Alternatives and similar repositories for control-arena

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

• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆132Updated this week
• Cadenza-Labs / sleeper-agents
  ☆10Updated 10 months ago
• METR / task-standard
  METR Task Standard
  ☆146Updated 3 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆223Updated 7 months ago
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆42Updated this week
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆64Updated 3 weeks 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 …
  ☆172Updated this week
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆92Updated this week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆245Updated 4 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆89Updated 3 months ago
• redwoodresearch / alignment_faking_public
  ☆58Updated 4 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆100Updated 2 months ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆70Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 3 years ago
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆34Updated last year
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆92Updated last year
• aypan17 / machiavelli
  ☆132Updated 6 months 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
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆213Updated last year
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆182Updated 6 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆31Updated 11 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆55Updated 6 months ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 5 months ago
• METR / public-tasks
  ☆92Updated 2 months ago
• callummcdougall / sae_visualizer
  ☆27Updated last year
• jacobdunefsky / transcoder_circuits
  ☆112Updated 6 months ago
• google-deepmind / mishax
  ☆129Updated last month
• safety-research / safety-examples
  ☆14Updated last week
• google-deepmind / dangerous-capability-evaluations
  ☆54Updated 7 months ago
• longtermrisk / openweights
  A python sdk for LLM finetuning and inference on runpod infrastructure
  ☆11Updated last week