METR / task-standardLinks
METR Task Standard
☆158Updated 6 months ago
Alternatives and similar repositories for task-standard
Users that are interested in task-standard are comparing it to the libraries listed below
Sorting:
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆88Updated this week
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆108Updated last week
- Collection of evals for Inspect AI☆209Updated last week
- ☆101Updated 5 months ago
- Mechanistic Interpretability Visualizations using React☆280Updated 8 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆212Updated 8 months ago
- ☆238Updated 10 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆223Updated 2 weeks ago
- Inference API for many LLMs and other useful tools for empirical research☆66Updated last week
- ☆98Updated 4 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- ☆56Updated 3 weeks ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆112Updated last year
- ☆291Updated last year
- A toolkit for describing model features and intervening on those features to steer behavior.☆197Updated 9 months ago
- Machine Learning for Alignment Bootcamp☆77Updated 3 years ago
- ☆195Updated 5 months ago
- Open source interpretability artefacts for R1.☆158Updated 4 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 2 years ago
- ☆139Updated last week
- ☆126Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆630Updated this week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆206Updated last week
- ☆138Updated last month
- ☆29Updated last year
- ☆26Updated 2 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆260Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- (Model-written) LLM evals library☆18Updated 8 months ago
- Tools for studying developmental interpretability in neural networks.☆101Updated 2 months ago