본문으로 건너뛰기
Juhyeon's Blog
Search
검색
다크 모드
라이트 모드
탐색기
태그: activation-steering
6건의 항목
2026년 11월 01일
Exploring the Personality Traits of LLMs through Latent Features Steering
paper
interpretability
LLM-personality
activation-steering
SAE
AI-safety
2026년 11월 01일
Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations
paper
interpretability
mechanistic-interpretability
alignment-auditing
LLM
anthropic
unsupervised-explanation
activation-steering
transformer-circuits
2026년 11월 01일
PERSONA VECTORS - MONITORING AND CONTROLLING CHARACTER TRAITS IN LANGUAGE MODELS
persona-vector
activation-steering
interpretability
ai-safety
finetuning
linear-representation
white-box
2026년 11월 01일
Persona Vectors in Games - Measuring and Steering Strategies via Activation Vectors
persona-vector
activation-steering
game-theory
strategic-behavior
CAA
interpretability
white-box
rhetoric-strategy-gap
2026년 11월 01일
Towards Steering without Sacrifice - Principled Training of Steering Vectors for Prompt-only Interventions
steering-vectors
activation-steering
LLM-control
representation-learning
scaling-laws
interpretability
2026년 11월 01일
Why Do LLMs Struggle in Strategic Play - Broken Links Between Observations, Beliefs, and Actions
논문
strategic-reasoning
mechanistic-interpretability
theory-of-mind
probing
activation-steering