This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen, Carl Vondrick, and Chengzhi Mao.
☆59Dec 9, 2024Updated last year
Alternatives and similar repositories for selfie
Users that are interested in selfie are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆36Nov 16, 2025Updated 9 months ago
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆17Apr 24, 2024Updated 2 years ago
- Sparse Autoencoder Training Library☆58May 1, 2025Updated last year
- code of paper "Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM"☆14Nov 17, 2023Updated 2 years ago
- ☆12Oct 23, 2022Updated 3 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆30Aug 2, 2024Updated 2 years ago
- Applying SAEs for fine-grained control☆27Dec 15, 2024Updated last year
- Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…☆32Apr 20, 2024Updated 2 years ago
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆14Jan 26, 2025Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆274Feb 27, 2026Updated 6 months ago
- TACL 2025: Investigating Adversarial Trigger Transfer in Large Language Models☆20Aug 17, 2025Updated last year
- ☆183May 1, 2026Updated 4 months ago
- Social Network Analysis and STEM Education is designed to prepare researchers to apply network analysis in order to better understand and…☆15Jul 14, 2025Updated last year
- This is the oficial repository for "Safer-Instruct: Aligning Language Models with Automated Preference Data"☆17Feb 22, 2024Updated 2 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- [EMNLP 2026] PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization☆18Aug 21, 2026Updated last week
- ☆12Apr 25, 2025Updated last year
- [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"☆15Jun 21, 2024Updated 2 years ago
- Using sparse coding to find distributed representations used by neural networks.☆312Nov 10, 2023Updated 2 years ago
- ☆17Feb 14, 2024Updated 2 years ago
- Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals; ACL 2024☆13May 24, 2024Updated 2 years ago
- PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses(COLM 2026)☆28Updated this week
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆22Dec 14, 2024Updated last year
- ☆15May 15, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆17Aug 1, 2025Updated last year
- ☆33Nov 28, 2024Updated last year
- ☆16Jul 23, 2024Updated 2 years ago
- ☆34Nov 7, 2024Updated last year
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆68May 31, 2024Updated 2 years ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆131Mar 22, 2024Updated 2 years ago
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆37May 26, 2025Updated last year
- This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".☆35Mar 11, 2025Updated last year
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆581Jan 28, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆179May 29, 2025Updated last year
- ☆223Oct 14, 2025Updated 10 months ago
- ☆18Jun 3, 2026Updated 2 months ago
- Algebraic value editing in pretrained language models☆71Nov 1, 2023Updated 2 years ago
- ☆20May 1, 2025Updated last year
- [NeurIPS 2025@FoRLM] R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search☆17Jan 24, 2026Updated 7 months ago
- An official implementation of "Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective" (KDD 2024)☆12Sep 16, 2024Updated last year