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.
  ☆94Updated this week
• METR / public-tasks
  ☆96Updated 2 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆139Updated this week
• UKGovernmentBEIS / control-arena
  ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…
  ☆60Updated this week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆251Updated 5 months ago
• Cadenza-Labs / sleeper-agents
  ☆10Updated 10 months ago
• METR / RE-Bench
  ☆76Updated last month
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆200Updated 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.
  ☆214Updated last year
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆47Updated last week
• google-deepmind / dangerous-capability-evaluations
  ☆54Updated 8 months ago
• redwoodresearch / alignment_faking_public
  ☆62Updated last week
• poking-agents / modular-public
  ☆22Updated this week
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 5 months ago
• anthropics / evals
  ☆274Updated 11 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆72Updated 3 years ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆223Updated 8 months ago
• google-deepmind / mishax
  ☆131Updated 2 months ago
• emergent-misalignment / emergent-misalignment
  ☆152Updated 2 months ago
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆15Updated 3 years ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆184Updated 6 months ago
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆140Updated last month
• longtermrisk / openweights
  A python sdk for LLM finetuning and inference on runpod infrastructure
  ☆11Updated last week
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆126Updated 2 years ago
• amack315 / unsupervised-steering-vectors
  ☆31Updated last year
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆105Updated last year
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆204Updated last week
• callummcdougall / sae_visualizer
  ☆28Updated last year
• ndif-team / ndif
  The NDIF server, which performs deep inference and serves nnsight requests remotely
  ☆28Updated this week