LRudL / sad
Situational Awareness Dataset
☆19Updated 3 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for sad
- A library for efficient patching and automatic circuit discovery.☆31Updated last month
- ☆32Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆25Updated 5 months ago
- ☆20Updated last week
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆62Updated 5 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆61Updated last week
- Measuring the situational awareness of language models☆33Updated 9 months ago
- Sparse Autoencoder Training Library☆27Updated 3 weeks ago
- Algebraic value editing in pretrained language models☆57Updated last year
- ☆11Updated 2 years ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆16Updated 3 weeks ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆84Updated 8 months ago
- Steering Llama 2 with Contrastive Activation Addition☆98Updated 5 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆62Updated last year
- ☆49Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆78Updated last year
- ☆71Updated 3 months ago
- Tasks for describing differences between text distributions.☆16Updated 3 months ago
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆48Updated 7 months ago
- Augmenting Statistical Models with Natural Language Parameters☆17Updated 2 months ago
- ☆107Updated this week
- A mechanistic approach for understanding and detecting factual errors of large language models.☆39Updated 4 months ago
- Official implementation of MAIA, A Multimodal Automated Interpretability Agent☆62Updated 3 months ago
- Repo for: When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment☆38Updated last year