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
  ☆169Updated 10 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆303Updated last year
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆90Updated last week
• TransluceAI / docent
  ☆75Updated 2 weeks ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆262Updated last year
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆320Updated last week
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆224Updated 3 weeks ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆233Updated last year
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆285Updated last year
• redwoodresearch / alignment_faking_public
  ☆82Updated 2 months ago
• Butanium / nnterp
  Unified access to Large Language Model modules using NNsight
  ☆70Updated this week
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆236Updated 4 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆135Updated 10 months ago
• emergent-misalignment / emergent-misalignment
  ☆236Updated last month
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆251Updated last year
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated last year
• ajobi-uhc / seer
  This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix …
  ☆81Updated 2 weeks ago
• anthropics / evals
  ☆319Updated last year
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆123Updated 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 …
  ☆234Updated last week
• saprmarks / feature-circuits
  ☆197Updated 2 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆117Updated 6 months ago
• METR / public-tasks
  ☆113Updated last month
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆745Updated last week
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• safety-research / safety-examples
  ☆21Updated last month
• adamkarvonen / SAEBench
  ☆138Updated this week
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆128Updated last month
• amack315 / unsupervised-steering-vectors
  ☆36Updated last year
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆216Updated last week