Neuron registration trends
The alpha price in τ, day by day, and what moved it each way.
Log change over the last 30 days −2.82%: protocol buys +0.04%, root sells −0.51%, users net +1.56%, cross-subnet −3.90%, unattributed −0.0028%.
The chart follows the alpha price in τ. Each period starts at its opening price and steps through the mechanisms below, in a fixed order, to its closing price: a step that rises pushed the price up, one that falls pushed it down, and its height is how far it moved the price. A thin line carries each close into the next period’s open; it is dashed where the two differ. The faint candle behind each period is the market’s own open, high, low and close, for context.
With many periods on screen (90 days, or hours), the steps would be too thin to read, so the chart draws the price as a line instead and colours each period by the mechanism that moved it most. Hover a period for the full step-by-step breakdown.
Not here, because they do not move the spot price: the per-block TAO injection into the pool, and burns.
All figures are log changes, not simple percentage changes, so the parts add up exactly to the total; on big moves the two differ (a 10% log fall is a 9.5% price fall).
2026-11-04 UTC, as of ≈00:27 UTC (block 9,429,031)
The day isn’t over yet, so these figures keep changing. They are in no daily total, average or rank.
Building tools that explain how language models work—sparse autoencoders, probes, and steering vectors—requires costly evaluation infrastructure and subjective scoring. Academic labs and industry teams duplicate this work separately, with no shared standard for measuring tool utility or comparing approaches across organizations.
A decentralized network of evaluators can pool resources to grade interpretability tools against consistent criteria, removing the need for centralized benchmarking. Miners publish candidate tools on persistent endpoints; independent evaluators run lane-specific protocols, record verdicts with verifiable charges, and publish results on-chain. Competition incentivizes both tool quality and fair evaluation.
Aurelius Protocol (Bittensor subnet 37) implements this as a competitive subnet where miners train SAEs or build other interpretability tools, stage them for evaluation windows, and earn rewards based on measured usefulness. Work-token credit (purchased with subnet alpha) commits submissions to evaluation; results are recorded with transparent scoring and per-lane rules published in advance.
Auto-generated from the GitHub repository and may not reflect the latest changes.
Aurelius Protocol is Bittensor subnet 37 where miners build and submit tools that explain and work with language models, competing for rewards based on usefulness. The first lane focuses on Sparse Autoencoders (SAEs) that miners train, submit for evaluation, and are ranked by performance. Rewards are scaled by subnet 37 alpha holdings and depend on winning lane-specific evaluations.
Aurelius is a competitive subnet where miners run public endpoints advertising staged candidate tools (initially SAEs). The miner component serves candidates, handles wallet/hotkey authentication, manages journal-based submission tracking, and publishes endpoint metadata on-chain. Miners purchase work-token credit (WT) by spending alpha via a verified funding client.
Evaluators pull staged candidates from miner endpoints, run lane-specific evaluations, and record verdicts with charges/refunds on-chain. Each lane has independent evaluation protocols and staging/window mechanics. Miner state (journal, nonce DB, wallet) persists across restarts.
Each tool type (SAEs, probes, steering vectors, etc.) has its own lane with specific evaluation rules. Miners train and submit tools, which are evaluated according to lane criteria. Scoring is competitive within lanes.
Alpha spent on WT purchases no longer counts toward payout multiplier. Charges are applied to committed submissions after epochs close, with refunds possible. Winners and scores are recorded in a ladder ranking system.
The sections above were auto-generated from the GitHub repository and may not reflect the latest changes. View repository (github.com, opens in a new tab, external site)
Decentralized Alignment of Artificial Intelligence
This information was auto-extracted from the GitHub repository and may be incomplete or out of date. Always refer to the subnet's GitHub repository (github.com, opens in a new tab, external site) for the latest instructions.
Not yet verified: Notes
Not found in the repository docs.
Machine-extracted from the subnet's repository docs; may be wrong or out of date. Check the repository before buying or renting hardware. Open the repository (github.com, opens in a new tab, external site) · Extracted 26 Oct 2026
Clone repository, install Python 3.12 via uv, sync dependencies with bt extra, and activate virtual environment
git clone https://github.com/Aurelius-Protocol/Aurelius-Protocol.git && cd Aurelius-Protocol && uv python install 3.12 && uv sync --all-packages --extra bt --no-dev --frozen --python 3.12 && source .venv/bin/activate
Create hotkey-only wallet copy on wallet machine, then copy to serving machine with proper permissions (0700 directories, 0600 files)
python scripts/prepare_wallet_view.py --source "$HOME/.bittensor/wallets" --output "$PWD/miner-wallets" --wallet miner --hotkey default --hotkey-ss58 YOUR_REGISTERED_HOTKEY_SS58
Configure environment variables from .env.example template, export them, and create required directories with proper permissions
cp .env.example .env && edit .env with required values && set -a && . ./.env && set +a && umask 077 && mkdir -p "$AURELIUS_MINER_DATA" "$AURELIUS_AXON_PUBLISH_STATE_DIR" "$(dirname "$AURELIUS_BITTENSOR_NONCE_DB")" "$(dirname "$AURELIUS_MINER_JOURNAL")" && chmod 700 "$AURELIUS_AXON_PUBLISH_STATE_DIR"
Start miner server to publish endpoint and serve staged candidates. Allow inbound TCP 8091; keep port 8092 private for local health checks
aurelius-miner serve --netuid 37 --port 8091
Buy work-tokens (WT) with subnet 37 alpha on wallet machine to fund evaluations. Preview first, then rerun with --execute to send(optional)
aurelius-miner fund --alpha 10 --wallet-name miner --wallet-path "$HOME/.bittensor/wallets" --intent-dir "$PWD/funding/purchase-001"
Build and submit SAE candidate. Train SAE according to lane specifications, validate bundle, upload to repository, and stage for evaluation window
Follow Lane 1 guide to train compatible SAE, run aurelius-sae check on bundle, upload with aurelius-sae-upload, then stage with aurelius-sae-stage
After epoch closes, check evaluation verdict, explanation, measured scores, ladder rank, and whether charges or refunds were recorded
aurelius-sae status --refresh --accounting --netuid 37
| Day (UTC) | Share |
|---|---|
| 2026-11-03 | 0.0001% |
| 2026-11-02 | 0.0001% |
| 2026-11-01 | 0.0001% |
| 2026-10-31 | 0.0001% |
| 2026-10-30 | 0.0001% |
| 2026-10-29 | 0.0001% |
| 2026-10-28 | 0.0001% |
| 2026-10-27 | 0.0001% |
| 2026-10-26 | 0.0001% |
| 2026-10-25 | 0.0001% |
| 2026-10-24 | 0.0001% |
| 2026-10-23 | 0.0001% |
| 2026-10-22 | 0.0001% |
| 2026-10-21 | 0.0001% |
| 2026-10-20 | 0.0001% |
| 2026-10-19 | 0.0001% |
| 2026-10-18 | 0.0001% |
| 2026-10-17 | 0.00% |
| 2026-10-16 | 0.0001% |
| 2026-10-15 | 0.0001% |
| 2026-10-14 | 0.0001% |
| 2026-10-13 | 0.0022% |
| 2026-10-12 | 0.01% |
| 2026-10-11 | 0.01% |
| 2026-10-10 | 0.01% |
| 2026-10-09 | 0.01% |
| 2026-10-08 | 0.0003% |
| 2026-10-07 | 0.00% |
| 2026-10-06 | 0.00% |
| 2026-10-05 | 0.00% |
| 2026-10-04 | 0.00% |
| 2026-10-03 | 0.00% |
| 2026-10-02 | 0.00% |
| 2026-10-01 | 0.00% |
| 2026-09-30 | 0.00% |
| 2026-09-29 | 0.00% |
| 2026-09-28 | 0.00% |
| 2026-09-27 | 0.00% |
| 2026-09-26 | 0.00% |
| 2026-09-25 | 0.00% |
| 2026-09-24 | 0.00% |
| 2026-09-23 | 0.00% |
| 2026-09-22 | 0.00% |
| 2026-09-21 | 0.00% |
| 2026-09-20 | 0.00% |
| 2026-09-19 | 0.00% |
| 2026-09-18 | 0.00% |
| 2026-09-17 | 0.00% |
| 2026-09-16 | 0.00% |
| 2026-09-15 | 0.00% |
| 2026-09-14 | 0.00% |
| 2026-09-13 | 0.00% |
| 2026-09-12 | 0.00% |
| 2026-09-11 | 0.00% |
| 2026-09-10 | 0.00% |
| 2026-09-09 | 0.00% |
| 2026-09-08 | 0.00% |
| 2026-09-07 | 0.00% |
| 2026-09-06 | 0.00% |
| 2026-09-05 | 0.00% |
| 2026-09-04 | 0.00% |
| 2026-09-03 | 0.00% |
| 2026-09-02 | 0.00% |
| 2026-09-01 | 0.00% |
| 2026-08-31 | 0.00% |
| 2026-08-30 | 0.00% |
| 2026-08-29 | 0.00% |
| 2026-08-28 | 0.00% |
| 2026-08-27 | 0.00% |
| 2026-08-26 | 0.00% |
| 2026-08-25 | 0.00% |
| 2026-08-24 | 0.00% |
| 2026-08-23 | 0.00% |
| 2026-08-22 | 0.00% |
| 2026-08-21 | 0.00% |
| 2026-08-20 | 0.00% |
| 2026-08-19 | 0.00% |
| 2026-08-18 | 0.00% |
| 2026-08-17 | 0.00% |
| 2026-08-16 | 0.00% |
| 2026-08-15 | 0.00% |
| 2026-08-14 | 0.00% |
| 2026-08-13 | 0.00% |
| 2026-08-12 | 0.00% |
| 2026-08-11 | 0.00% |
| 2026-08-10 | 0.00% |
| 2026-08-09 | 0.00% |
| 2026-08-08 | 0.00% |
| 2026-08-07 | 0.00% |
| 2026-08-06 | 0.00% |
