Alternatives and similar repositories for control-arena:

Users that are interested in control-arena are comparing it to the libraries listed below

• METR / task-standard
  METR Task Standard
  ☆146Updated 2 months ago
• Cadenza-Labs / sleeper-agents
  ☆10Updated 9 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆241Updated 4 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆115Updated this week
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆33Updated this week
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆89Updated last week
• ArthurConmy / Automatic-Circuit-Discovery
  ☆218Updated 6 months ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆209Updated last year
• METR / public-tasks
  ☆89Updated last month
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆88Updated 3 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆169Updated this week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆197Updated 4 months ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆70Updated last year
• saprmarks / feature-circuits
  ☆161Updated 2 weeks ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆102Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆95Updated 2 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆178Updated 5 months ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 4 months ago
• callummcdougall / sae_visualizer
  ☆26Updated last year
• poking-agents / modular-public
  ☆21Updated 3 weeks ago
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆72Updated 2 years ago
• ApolloResearch / sample
  Repository with sample code using Apollo's suggested engineering practices
  ☆8Updated 4 months ago
• safety-research / safety-examples
  ☆13Updated last week
• METR / RE-Bench
  ☆72Updated 2 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆241Updated 9 months ago
• adamkarvonen / SAEBench
  ☆85Updated 2 weeks ago
• amack315 / unsupervised-steering-vectors
  ☆31Updated 11 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆91Updated last year
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆52Updated 5 months ago