Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Roh, Youngji, Cho, Hyunjin, Kim, Jaehyung
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.00029
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911690108436480
author Roh, Youngji
Cho, Hyunjin
Kim, Jaehyung
author_facet Roh, Youngji
Cho, Hyunjin
Kim, Jaehyung
contents Large Language Models (LLMs) exhibit highly anisotropic internal representations, often characterized by massive activations, a phenomenon where a small subset of feature dimensions possesses magnitudes significantly larger than the rest. While prior works view these extreme dimensions primarily as artifacts to be managed, we propose a distinct perspective: these dimensions serve as intrinsic interpretable functional units arising from domain specialization. Specifically, we propose a simple magnitude-based criterion to identify Domain-Critical Dimensions in a training-free manner. Our analyses reveal that such dimensions behave as interpretable semantic detectors for symbolic/quantitative patterns or domain-specific terms. In addition, we introduce Critical Dimension Steering, which applies activation steering exclusively to the identified dimensions. Empirical results show that this approach outperforms conventional whole-dimension steering in domain adaptation and jailbreaking scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00029
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models
Roh, Youngji
Cho, Hyunjin
Kim, Jaehyung
Computation and Language
Large Language Models (LLMs) exhibit highly anisotropic internal representations, often characterized by massive activations, a phenomenon where a small subset of feature dimensions possesses magnitudes significantly larger than the rest. While prior works view these extreme dimensions primarily as artifacts to be managed, we propose a distinct perspective: these dimensions serve as intrinsic interpretable functional units arising from domain specialization. Specifically, we propose a simple magnitude-based criterion to identify Domain-Critical Dimensions in a training-free manner. Our analyses reveal that such dimensions behave as interpretable semantic detectors for symbolic/quantitative patterns or domain-specific terms. In addition, we introduce Critical Dimension Steering, which applies activation steering exclusively to the identified dimensions. Empirical results show that this approach outperforms conventional whole-dimension steering in domain adaptation and jailbreaking scenarios.
title Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2603.00029