google-deepmind / dangerous-capability-evaluationsLinks
☆55Updated this week
Alternatives and similar repositories for dangerous-capability-evaluations
Users that are interested in dangerous-capability-evaluations are comparing it to the libraries listed below
Sorting:
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆111Updated last year
- METR Task Standard☆156Updated 6 months ago
- ☆95Updated 3 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- ☆136Updated 4 months ago
- Collection of evals for Inspect AI☆198Updated this week
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- ☆137Updated 2 weeks ago
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆127Updated 2 years ago
- Measuring the situational awareness of language models☆37Updated last year
- Open source interpretability artefacts for R1.☆157Updated 3 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆86Updated last year
- ☆99Updated 4 months ago
- ☆287Updated last year
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆80Updated this week
- ☆182Updated 4 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- we got you bro☆36Updated last year
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆103Updated last week
- ☆24Updated 9 months ago
- ☆28Updated last year
- Functional Benchmarks and the Reasoning Gap☆88Updated 10 months ago
- Inference API for many LLMs and other useful tools for empirical research☆61Updated this week
- A toolkit for describing model features and intervening on those features to steer behavior.☆195Updated 8 months ago
- ☆52Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 8 months ago
- Extract full next-token probabilities via language model APIs☆247Updated last year