Cover Image

Steered LLM Activations are Non-Surjective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mishra, Aayush, Khashabi, Daniel, Liu, Anqi
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
by: Mishra, Aayush, et al.
Published: (2025)

Do pretrained Transformers Learn In-Context by Gradient Descent?
by: Shen, Lingfeng, et al.
Published: (2023)

Genomic Next-Token Predictors are In-Context Learners
by: Breslow, Nathan, et al.
Published: (2025)

Steer Like the LLM: Activation Steering that Mimics Prompting
by: Heyman, Geert, et al.
Published: (2026)

The Rogue Scalpel: Activation Steering Compromises LLM Safety
by: Korznikov, Anton, et al.
Published: (2025)

Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting
by: Wynn, Andrea, et al.
Published: (2025)

DECODE: Data-driven Energy Consumption Prediction leveraging Historical Data and Environmental Factors in Buildings
by: Mishra, Aditya, et al.
Published: (2023)

Dynamically Scaled Activation Steering
by: Ferrando, Alex, et al.
Published: (2025)

Minimizing Collateral Damage in Activation Steering
by: Nguyen, Tam, et al.
Published: (2026)

Activation Steering for Chain-of-Thought Compression
by: Azizi, Seyedarmin, et al.
Published: (2025)

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
by: Hedström, Anna, et al.
Published: (2025)

HyperSteer: Activation Steering at Scale with Hypernetworks
by: Sun, Jiuding, et al.
Published: (2025)

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
by: Jiang, Xinyan, et al.
Published: (2026)

BarrierSteer: LLM Safety via Learning Barrier Steering
by: Tran, Thanh Q., et al.
Published: (2026)

ODD: Overlap-aware Estimation of Model Performance under Distribution Shift
by: Mishra, Aayush, et al.
Published: (2025)

CBMAS: Cognitive Behavioral Modeling via Activation Steering
by: Ismail, Ahmed H., et al.
Published: (2026)

Test-time Diverse Reasoning by Riemannian Activation Steering
by: Khanh, Ly Tran Ho, et al.
Published: (2025)

Steering Large Language Model Activations in Sparse Spaces
by: Bayat, Reza, et al.
Published: (2025)

Angular Steering: Behavior Control via Rotation in Activation Space
by: Vu, Hieu M., et al.
Published: (2025)

Multi-property Steering of Large Language Models with Dynamic Activation Composition
by: Scalena, Daniel, et al.
Published: (2024)

Programming Refusal with Conditional Activation Steering
by: Lee, Bruce W., et al.
Published: (2024)

SAKE: Steering Activations for Knowledge Editing
by: Scialanga, Marco, et al.
Published: (2025)

Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection
by: Kang, Minjae, et al.
Published: (2026)

Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement
by: Wang, Anyi, et al.
Published: (2025)

Steering LLM Reasoning Through Bias-Only Adaptation
by: Sinii, Viacheslav, et al.
Published: (2025)

Graph-Regularized Sparse Autoencoders for LLM Safety Steering
by: Yeon, Jehyeok, et al.
Published: (2025)

Endogenous Resistance to Activation Steering in Language Models
by: McKenzie, Alex, et al.
Published: (2026)

On the Non-Identifiability of Steering Vectors in Large Language Models
by: Venkatesh, Sohan, et al.
Published: (2026)

Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models
by: Yang, Jiaxi, et al.
Published: (2026)

Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
by: Bigelow, Eric, et al.
Published: (2025)

MASteer: Multi-Agent Adaptive Steer Strategy for End-to-End LLM Trustworthiness Repair
by: Li, Changqing, et al.
Published: (2025)

Preemptive Detection and Steering of LLM Misalignment via Latent Reachability
by: Karnik, Sathwik, et al.
Published: (2025)

Extracting Unlearned Information from LLMs with Activation Steering
by: Seyitoğlu, Atakan, et al.
Published: (2024)

Steering Llama 2 via Contrastive Activation Addition
by: Panickssery, Nina, et al.
Published: (2023)

MidSteer: Optimal Affine Framework for Steering Generative Models
by: Gaintseva, Tatiana, et al.
Published: (2026)

Fast Forward: Accelerating LLM Prefill with Predictive FFN Sparsity
by: Gautam, Aayush, et al.
Published: (2026)

Correctness-Optimized Residual Activation Lens (CORAL): Transferrable and Calibration-Aware Inference-Time Steering
by: Miao, Miranda Muqing, et al.
Published: (2026)

MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
by: Ding, Chenlu, et al.
Published: (2025)

Steer LLM Latents for Hallucination Detection
by: Park, Seongheon, et al.
Published: (2025)

REAct: Rational Exponential Activation for Better Learning and Generalization in PINNs
by: Mishra, Sourav, et al.
Published: (2025)