Alternatives and similar repositories for modular-public:

Users that are interested in modular-public are comparing it to the libraries listed below

• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆74Updated this week
• METR / task-standard
  METR Task Standard
  ☆135Updated 2 weeks ago
• METR / ai-rd-tasks
  ☆51Updated last week
• Cadenza-Labs / sleeper-agents
  ☆10Updated 6 months ago
• METR / public-tasks
  ☆79Updated last week
• anthropics / evals
  ☆247Updated 6 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆78Updated last month
• redwoodresearch / remix_public
  ☆19Updated last year
• google-deepmind / dangerous-capability-evaluations
  ☆48Updated 3 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆220Updated last month
• callummcdougall / sae_visualizer
  ☆25Updated 9 months ago
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆26Updated 7 months ago
• rgreenblatt / arc_draw_more_samples_pub
  Draw more samples
  ☆184Updated 6 months ago
• AblateIt / finetune-study
  Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.
  ☆82Updated last year
• ScalingIntelligence / Archon
  Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.
  ☆154Updated 2 months ago
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆230Updated 10 months ago
• haizelabs / sphynx
  Sphynx Hallucination Induction
  ☆51Updated 5 months ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆93Updated 10 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆13Updated 2 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆47Updated this week
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆206Updated 11 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆150Updated 2 months ago
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆70Updated 2 years ago
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆18Updated last year
• allenai / discoverybench
  Discovering Data-driven Hypotheses in the Wild
  ☆51Updated 2 months ago
• google-deepmind / mishax
  ☆115Updated this week
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆192Updated last week
• danielmamay / mlab
  Machine Learning for Alignment Bootcamp (MLAB).
  ☆24Updated 2 years ago
• adamkarvonen / SAEBench
  ☆41Updated this week
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆114Updated 7 months ago