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
  ☆151Updated 4 months ago
• redwoodresearch / alignment_faking_public
  ☆66Updated last month
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆167Updated this week
• ArthurConmy / Automatic-Circuit-Discovery
  ☆227Updated 8 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆257Updated 6 months ago
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆49Updated last week
• google-deepmind / dangerous-capability-evaluations
  ☆55Updated 9 months ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆96Updated this week
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆67Updated 2 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆108Updated 4 months ago
• Cadenza-Labs / sleeper-agents
  ☆11Updated 11 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆95Updated this week
• callummcdougall / sae_visualizer
  ☆28Updated 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 …
  ☆185Updated last week
• aypan17 / machiavelli
  ☆134Updated 7 months ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 6 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆202Updated 6 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆190Updated 7 months ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆108Updated last year
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆214Updated 9 months ago
• adamkarvonen / SAEBench
  ☆101Updated 3 weeks ago
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆99Updated 4 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆35Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆158Updated last year
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆94Updated last year
• centerforaisafety / wmdp
  WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…
  ☆127Updated 3 weeks ago
• saprmarks / feature-circuits
  ☆175Updated 2 months ago
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆255Updated last year
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆71Updated last year
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆252Updated 11 months ago