MinhxLe / subliminal-learningLinks
☆95Updated last month
Alternatives and similar repositories for subliminal-learning
Users that are interested in subliminal-learning are comparing it to the libraries listed below
Sorting:
- ☆142Updated last week
- ☆57Updated last month
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆128Updated 3 years ago
- Code for "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs"☆54Updated 6 months ago
- Open source interpretability artefacts for R1.☆158Updated 5 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated this week
- ☆108Updated 7 months ago
- Functional Benchmarks and the Reasoning Gap☆88Updated 11 months ago
- ☆99Updated 4 months ago
- ☆103Updated 6 months ago
- METR Task Standard☆159Updated 7 months ago
- ☆68Updated 3 weeks ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆111Updated this week
- ☆26Updated 3 months ago
- ☆53Updated last year
- ☆25Updated 10 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆201Updated 10 months ago
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- we got you bro☆36Updated last year
- Training-Ready RL Environments + Evals☆101Updated this week
- Draw more samples☆193Updated last year
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆53Updated 5 months ago
- An attribution library for LLMs☆42Updated last year
- A dataset of alignment research and code to reproduce it☆77Updated 2 years ago
- ☆29Updated last year
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.☆31Updated 4 months ago
- Public repository containing METR's DVC pipeline for eval data analysis☆108Updated 5 months ago
- Measuring the situational awareness of language models☆38Updated last year
- ☆123Updated last year
- 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