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
  ☆163Updated 8 months ago
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆77Updated last week
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆272Updated this week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆296Updated 10 months ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 10 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆248Updated last year
• redwoodresearch / alignment_faking_public
  ☆79Updated 3 weeks ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆224Updated 10 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆127Updated 8 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆209Updated 11 months ago
• saprmarks / feature-circuits
  ☆192Updated 2 weeks ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆278Updated last year
• TransluceAI / docent
  ☆57Updated last month
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆120Updated last year
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆221Updated this week
• google-deepmind / dangerous-capability-evaluations
  ☆61Updated last month
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆112Updated 4 months ago
• Butanium / nnterp
  Unified access to Large Language Model modules using NNsight
  ☆52Updated last week
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆230Updated 2 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆238Updated last year
• jacobdunefsky / transcoder_circuits
  ☆183Updated 11 months ago
• emergent-misalignment / emergent-misalignment
  ☆222Updated 7 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆211Updated this week
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆74Updated 2 years ago
• METR / public-tasks
  ☆104Updated 2 weeks ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆118Updated last week
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆191Updated last year
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆692Updated this week
• safety-research / safety-examples
  ☆19Updated last week
• amack315 / unsupervised-steering-vectors
  ☆36Updated last year