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
  ☆148Updated 4 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆144Updated this week
• Cadenza-Labs / sleeper-agents
  ☆10Updated 10 months ago
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆48Updated last week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆253Updated 5 months ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 5 months ago
• safety-research / safety-examples
  ☆15Updated last month
• longtermrisk / openweights
  A python sdk for LLM finetuning and inference on runpod infrastructure
  ☆11Updated this week
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆94Updated last week
• redwoodresearch / alignment_faking_public
  ☆62Updated 2 weeks ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆223Updated 8 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 …
  ☆181Updated this week
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆91Updated 4 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆103Updated 3 months ago
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆73Updated 3 years ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆201Updated 5 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆185Updated 6 months ago
• callummcdougall / sae_visualizer
  ☆28Updated last year
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆214Updated last year
• google-deepmind / dangerous-capability-evaluations
  ☆54Updated 8 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆126Updated 2 years ago
• ARBORproject / arborproject.github.io
  ☆75Updated 3 months ago
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆15Updated 3 years ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆65Updated last month
• saprmarks / feature-circuits
  ☆171Updated last month
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆205Updated this week
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆69Updated last year
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆106Updated last year
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆140Updated last month
• adamkarvonen / SAEBench
  ☆97Updated last month