Alternatives and similar repositories for task-standard:

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

• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆78Updated this week
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 2 months ago
• METR / public-tasks
  ☆83Updated last month
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆232Updated 2 months ago
• poking-agents / modular-public
  ☆15Updated this week
• Cadenza-Labs / sleeper-agents
  ☆10Updated 7 months ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆208Updated last year
• METR / ai-rd-tasks
  ☆61Updated 3 weeks ago
• google-deepmind / dangerous-capability-evaluations
  ☆50Updated 4 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆76Updated this week
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆70Updated 2 years ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆203Updated 4 months ago
• amack315 / unsupervised-steering-vectors
  ☆29Updated 9 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆182Updated 2 months ago
• google-deepmind / mishax
  ☆121Updated last week
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆93Updated 11 months ago
• redwoodresearch / alignment_faking_public
  ☆40Updated last month
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆88Updated this week
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆84Updated 3 weeks ago
• callummcdougall / sae_visualizer
  ☆25Updated 10 months ago
• aypan17 / machiavelli
  ☆128Updated 3 months ago
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 2 years ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆195Updated last week
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆71Updated last year
• EleutherAI / delphi
  ☆151Updated this week
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆181Updated 4 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆15Updated 3 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆216Updated 7 months ago
• adamkarvonen / SAEBench
  ☆52Updated this week