Alternatives and similar repositories for task-standard

Users that are interested in task-standard are comparing it to the libraries listed below

• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆73Updated this week
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆99Updated 2 weeks ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆178Updated this week
• METR / public-tasks
  ☆99Updated 3 months ago
• METR / RE-Bench
  ☆92Updated 2 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆260Updated 6 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆206Updated 6 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆55Updated 9 months ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆216Updated 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 …
  ☆192Updated last week
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆52Updated last week
• ArthurConmy / Automatic-Circuit-Discovery
  ☆231Updated 9 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆112Updated 4 months ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆109Updated last year
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆207Updated last week
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆191Updated 8 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆255Updated 11 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆122Updated last year
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆154Updated 2 months ago
• anthropics / evals
  ☆283Updated last year
• google-deepmind / mishax
  ☆134Updated 3 months ago
• emergent-misalignment / emergent-misalignment
  ☆168Updated 4 months ago
• amack315 / unsupervised-steering-vectors
  ☆32Updated last year
• aypan17 / machiavelli
  ☆137Updated 8 months ago
• saprmarks / feature-circuits
  ☆182Updated 3 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆127Updated 2 years ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 7 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆99Updated 2 weeks ago
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆74Updated 3 years ago
• LeonGuertler / TextArena
  A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
  ☆207Updated this week