WangLab

university

https://nlp.wustl.edu/

chenguangwang

wang-research-lab

Activity Feed Request to join this org

AI & ML interests

NLP

Recent Activity

ncrispino authored a paper 23 days ago

RepIt: Representing Isolated Targets to Steer Language Models

ncrispino updated a collection 24 days ago

LLM Interpretability

ncrispino updated a collection 24 days ago

LLM Interpretability

View all activity

Collections 4

View 4 collections

models 16

datasets 4

WangResearchLab/SteeringControl

Viewer • Updated 24 days ago • 71.6k • 660 • 1

WangResearchLab/te_dataset_hf

Viewer • Updated Apr 18 • 1.2k • 4

WangResearchLab/MLAN

Preview • Updated Nov 19, 2024 • 23 • 1

WangResearchLab/AgentInstruct

Viewer • Updated Nov 2, 2023 • 53 • 85 • 2

WangLab

AI & ML interests

Recent Activity

Collections 4

COSMIC: Generalized Refusal Direction Identification in LLM Activations

RepIt: Representing Isolated Targets to Steer Language Models

SteeringControl

WangResearchLab/SteeringControl

SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

COSMIC: Generalized Refusal Direction Identification in LLM Activations

RepIt: Representing Isolated Targets to Steer Language Models

SteeringControl

WangResearchLab/SteeringControl

SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

models 16

WangResearchLab/Yarn-Llama-2-13b-128k

WangResearchLab/Yarn-Llama-2-13b-64k

WangResearchLab/Yarn-Llama-2-13b-32k

WangResearchLab/Yarn-Llama-2-13b-16k

WangResearchLab/Yarn-Llama-2-13b-8k

WangResearchLab/Llama-2-13b-hf

WangResearchLab/Yarn-Llama-2-7b-128k

WangResearchLab/Yarn-Llama-2-7b-64k

WangResearchLab/Yarn-Llama-2-7b-32k

WangResearchLab/Yarn-Llama-2-7b-16k

datasets 4

WangResearchLab/SteeringControl

WangResearchLab/te_dataset_hf

WangResearchLab/MLAN

WangResearchLab/AgentInstruct

AI & ML interests

Recent Activity

Team members 3

Collections 4

models 16 Sort: Recently updated

datasets 4 Sort: Recently updated

models 16

datasets 4