TeunvdWeij / sandbaggingLinks
☆10Updated 7 months ago
Alternatives and similar repositories for sandbagging
Users that are interested in sandbagging are comparing it to the libraries listed below
Sorting:
- ☆16Updated last year
- (Model-written) LLM evals library☆18Updated 6 months ago
- ☆65Updated last month
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- Steering Llama 2 with Contrastive Activation Addition☆158Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆108Updated 4 months ago
- ☆54Updated 2 years ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆94Updated last year
- Inference API for many LLMs and other useful tools for empirical research☆49Updated this week
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆98Updated 4 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 7 months ago
- Repository with sample code using Apollo's suggested engineering practices☆9Updated 6 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- 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
- ☆31Updated last year
- A library for mechanistic anomaly detection☆22Updated 5 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆35Updated last year
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆58Updated 2 weeks ago
- ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…☆69Updated this week
- General-purpose activation steering library☆78Updated last month
- Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting☆17Updated 2 months ago
- ☆44Updated last year
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆127Updated 3 weeks ago
- ☆131Updated 7 months ago
- ☆227Updated 8 months ago
- Sparse probing paper full code.☆58Updated last year
- A python sdk for LLM finetuning and inference on runpod infrastructure☆11Updated last week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- ☆101Updated 3 weeks ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 3 months ago