METR / task-standardLinks
METR Task Standard
☆151Updated 4 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:
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆94Updated last week
- Collection of evals for Inspect AI☆155Updated this week
- ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…☆69Updated this week
- ☆98Updated 3 months ago
- ☆84Updated 2 months ago
- Mechanistic Interpretability Visualizations using React☆257Updated 6 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆216Updated last year
- ☆22Updated 3 weeks ago
- ☆55Updated 8 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆202Updated 6 months ago
- Machine Learning for Alignment Bootcamp☆74Updated 3 years ago
- ☆226Updated 8 months ago
- ☆31Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆126Updated 2 years ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆190Updated 7 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆108Updated 4 months ago
- Inference API for many LLMs and other useful tools for empirical research☆49Updated this week
- (Model-written) LLM evals library☆18Updated 6 months ago
- ☆156Updated 3 months ago
- Extract full next-token probabilities via language model APIs☆247Updated last year
- ☆134Updated 2 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆185Updated this week
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆207Updated 2 weeks ago
- ☆11Updated 11 months ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆108Updated last year
- Measuring the situational awareness of language models☆35Updated last year
- ☆133Updated 7 months ago
- Tools for studying developmental interpretability in neural networks.☆94Updated 5 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆250Updated 11 months ago
- Scale your LLM-as-a-judge.☆240Updated 2 weeks ago