google-deepmind / dangerous-capability-evaluationsLinks
☆55Updated 8 months ago
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:
- ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…☆69Updated this week
- ☆87Updated 2 months ago
- METR Task Standard☆151Updated 4 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆27Updated last year
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆108Updated last year
- ☆134Updated 2 months ago
- ☆133Updated 7 months ago
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- ☆22Updated 3 weeks ago
- Measuring the situational awareness of language models☆35Updated last year
- ☆28Updated last year
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆96Updated this week
- Collection of evals for Inspect AI☆155Updated this week
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆70Updated last year
- we got you bro☆35Updated 10 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆81Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆108Updated 4 months ago
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- ☆11Updated 11 months ago
- Functional Benchmarks and the Reasoning Gap☆87Updated 8 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆95Updated 2 weeks ago
- Sparse Autoencoder Training Library☆52Updated last month
- ☆98Updated 3 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 6 months ago
- ☆31Updated last year
- ☆65Updated last month
- ☆97Updated 4 months ago
- A dataset of alignment research and code to reproduce it☆77Updated 2 years ago
- ☆19Updated 2 years ago
- Open source interpretability artefacts for R1.☆149Updated 2 months ago