Cover Image

Activation Scaling for Steering and Interpreting Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Stoehr, Niklas, Du, Kevin, Snæbjarnarson, Vésteinn, West, Robert, Cotterell, Ryan, Schein, Aaron
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Context versus Prior Knowledge in Language Models
by: Du, Kevin, et al.
Published: (2024)

Gumbel Counterfactual Generation From Language Models
by: Ravfogel, Shauli, et al.
Published: (2024)

Contrastive Decoding for Synthetic Data Generation in Low-Resource Language Modeling
by: Ulm, Jannek, et al.
Published: (2025)

Controllable Context Sensitivity and the Knob Behind It
by: Minder, Julian, et al.
Published: (2024)

Taxonomy-Aware Evaluation of Vision-Language Models
by: Snæbjarnarson, Vésteinn, et al.
Published: (2025)

On the Proper Treatment of Units in Surprisal Theory
by: Kiegeland, Samuel, et al.
Published: (2026)

Transducing Language Models
by: Snæbjarnarson, Vésteinn, et al.
Published: (2026)

Layers at Similar Depths Generate Similar Activations Across LLM Architectures
by: Wolfram, Christopher, et al.
Published: (2025)

Discriminative Class Tokens for Text-to-Image Diffusion Models
by: Schwartz, Idan, et al.
Published: (2023)

A Distributional Perspective on Word Learning in Neural Language Models
by: Ficarra, Filippo, et al.
Published: (2025)

How Persuasive is Your Context?
by: Nguyen, Tu, et al.
Published: (2025)

Towards Explainability in Legal Outcome Prediction Models
by: Valvoda, Josef, et al.
Published: (2024)

Structured Voronoi Sampling
by: Amini, Afra, et al.
Published: (2023)

Transformers Can Represent $n$-gram Language Models
by: Svete, Anej, et al.
Published: (2024)

Interpretable Steering of Large Language Models with Feature Guided Activation Additions
by: Soo, Samuel, et al.
Published: (2025)

Linear Representations of Political Perspective Emerge in Large Language Models
by: Kim, Junsol, et al.
Published: (2025)

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

Better Estimation of the Kullback--Leibler Divergence Between Language Models
by: Amini, Afra, et al.
Published: (2025)

Cross-Lingual Activation Steering for Multilingual Language Models
by: Pokharel, Rhitabrat, et al.
Published: (2026)

Syntactic Control of Language Models by Posterior Inference
by: Xefteri, Vicky, et al.
Published: (2025)

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

Post-Training Language Models for Crosslingual Consistency
by: Liu, Tianyu, et al.
Published: (2026)

Generalized Measures of Anticipation and Responsivity in Online Language Processing
by: Giulianelli, Mario, et al.
Published: (2024)

From Language Models over Tokens to Language Models over Characters
by: Vieira, Tim, et al.
Published: (2024)

ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
by: Guang, Jiahui, et al.
Published: (2026)

Improving LLM Reasoning through Interpretable Role-Playing Steering
by: Wang, Anyi, et al.
Published: (2025)

Steering Awareness: Detecting Activation Steering from Within
by: Rivera, Joshua Fonseca, et al.
Published: (2025)

SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models
by: He, Zirui, et al.
Published: (2025)

Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering
by: Valentino, Marco, et al.
Published: (2025)

Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
by: Dumas, Clément, et al.
Published: (2024)

Improving Instruction-Following in Language Models through Activation Steering
by: Stolfo, Alessandro, et al.
Published: (2024)

Self-Steering Language Models
by: Grand, Gabriel, et al.
Published: (2025)

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

ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models
by: Anand, Nikhil, et al.
Published: (2026)

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
by: Zhao, Haiyan, et al.
Published: (2025)

DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion
by: Li, Yu, et al.
Published: (2024)

Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals
by: Torrielli, Federico, et al.
Published: (2026)

Locally Typical Sampling
by: Meister, Clara, et al.
Published: (2022)

Steering When Necessary: Flexible Steering Large Language Models with Backtracking
by: Cheng, Zifeng, et al.
Published: (2025)

Fusion Steering: Prompt-Specific Activation Control
by: Chang, Waldemar, et al.
Published: (2025)