Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering succeeds or fails remain poorly understood, as prior work has relied primarily on black-box outputs or LLM-based judges. In this study, we investigate whether the reliability of steering can be diagnosed using internal model signals. We focus on two information-theoretic measures: the entropy-derived Normalized Branching Factor (NBF), and the Kullback-Leibler (KL) divergence between steered activations and targeted concepts in the vocabulary space. We hypothesize that effective steering corresponds to structured entropy preservation and coherent KL alignment across decoding steps. Building on a reliability study demonstrating high inter-judge agreement between two architecturally distinct LLMs, we use LLM-generated annotations as ground truth and show that these mechanistic signals provide meaningful predictive power for identifying successful steering and estimating failure probability. We further introduce a stronger evaluation baseline for Contrastive Activation Addition (CAA) and Sparse Autoencoder-based steering, the two most widely adopted activation-steering methods.
Is Inference Mediated by Distinct Semantic Structures in LLMs? A Mechanistic Interpretation
University of Manchester（曼彻斯特大学）；University of Sheffield（谢菲尔德大学）；Idiap Research Institute（Idiap研究所）；CRUK National Biomarker Centre, University of Manchester（CRUK国家生物标志物中心，曼彻斯特大学）
Explaining Intrinsic Moral Self-Correction with Mechanistic Interpretability
Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan（通讯工程研究院，国立台湾大学）；MediaTek Research, Taipei, Taiwan（联发科研究，台北，台湾）；Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan（电气工程系，国立台湾大学）；Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan（电气工程系，国立清华大学）；AI Research Center (AINTU), National Taiwan University, Taipei, Taiwan（人工智能研究中心（AINTU），国立台湾大学）
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
The University of Hong Kong（香港大学）；Fudan University（复旦大学）；LMU Munich（慕尼黑大学）；Tsinghua University（清华大学）；Technische Universität Darmstadt（达姆施塔特技术大学）；Technische Universität Berlin（柏林技术大学）；Technische Universität Dresden（德累斯顿技术大学）；The Chinese University of Hong Kong（香港中文大学）；University of Pennsylvania（宾夕法尼亚大学）；Nanjing University（南京大学）；University of Manchester（曼彻斯特大学）；Dartmouth College（达特茅斯学院）；University of California Los Angeles（加州大学洛杉矶分校）；University of Michigan（密歇根大学）；Microsoft（微软）；Tencent（腾讯）
How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）
CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models
National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, Huazhong University of Science and Technology（华中科技大学国家大数据技术与系统工程技术研究中心、服务计算技术与系统实验室、集群与网格计算实验室）；Singapore Management University（新加坡管理大学）
Inducing language models to assert their own consciousness restores human beliefs and values
Google（谷歌）；University of Chicago（芝加哥大学）；University of London（伦敦大学）；University of Washington（华盛顿大学）；Northwestern University（西北大学）；Santa Fe Institute（圣达菲研究所）
Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs)
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg（卢森堡大学跨学科安全、可靠性与信任中心（SnT））；Amsterdam Business School, University of Amsterdam（阿姆斯特丹大学阿姆斯特丹商学院）；Stanford Graduate School of Business, Stanford University（斯坦福大学斯坦福商学院）
How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
University of California, Los Angeles（加州大学洛杉矶分校）；University of Alberta（阿尔伯塔大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Harvard University（哈佛大学）
Computer Science Department, TU Darmstadt（图宾根大学计算机科学系）；Lab1141；Aleph Alpha Research（Aleph Alpha研究）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；CERTAIN；Centre of Cognitive Science, TU Darmstadt（图宾根大学认知科学中心）
CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models
Department of Informatics, Universität Hamburg（汉堡大学信息学院）；The University of Sydney（悉尼大学）；Alibaba International Digital Commerce（阿里巴巴国际数字商业）；Institute of Psychology, Chinese Academy of Sciences（中国科学院心理研究所）
Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection
Saarland University（萨尔兰大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；TU Darmstadt（德累斯顿技术大学）；Centre for European Research in Trusted AI (CERTAIN)（欧洲可信AI研究中心）
Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias
AMAP, Alibaba Group（阿里巴巴集团AMAP实验室）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Southern California（南加州大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）
The Latin Substrate: How Language Models Represent and Mediate Script Choice
German Research Center for AI（德国人工智能研究中心）；Saarland University（萨尔兰大学）；Indian Institute of Technology, Madras（印度理工学院-马德拉斯）；Nilekani Centre at AI4Bharat（AI4Bharat的Nilekani中心）
