Alternatives and similar repositories for task-standard:

Users that are interested in task-standard are comparing it to the libraries listed below

• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆80Updated this week
• METR / public-tasks
  ☆84Updated this week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆233Updated 2 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆52Updated 5 months ago
• METR / RE-Bench
  ☆60Updated last month
• poking-agents / modular-public
  ☆15Updated 2 weeks ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆206Updated last year
• amack315 / unsupervised-steering-vectors
  ☆29Updated 10 months ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 3 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆184Updated 2 months ago
• google-deepmind / mishax
  ☆123Updated last month
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆115Updated 2 years ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆210Updated 5 months ago
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆71Updated 2 years ago
• Cadenza-Labs / sleeper-agents
  ☆10Updated 8 months ago
• rgreenblatt / arc_draw_more_samples_pub
  Draw more samples
  ☆186Updated 8 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆162Updated 4 months ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆93Updated last year
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆86Updated last month
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆87Updated this week
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆120Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 2 years ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆15Updated 3 months ago
• jacobdunefsky / transcoder_circuits
  ☆60Updated 3 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆197Updated this week
• anthropics / evals
  ☆258Updated 8 months ago
• callummcdougall / sae_visualizer
  ☆26Updated 11 months ago