Copertina

NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Weiqi, Miao, Yongliang, Zhao, Haiyan, Liu, Yanguang, Du, Mengnan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling
di: Miao, Yongliang, et al.
Pubblicazione: (2026)

SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection
di: Zhang, Huopu, et al.
Pubblicazione: (2025)

Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis
di: Li, Daoyang, et al.
Pubblicazione: (2024)

Tackling Polysemanticity with Neuron Embeddings
di: Foote, Alex
Pubblicazione: (2024)

Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation
di: Zhao, Haiyan, et al.
Pubblicazione: (2026)

Disentangling Polysemantic Neurons with a Null-Calibrated Polysemanticity Index and Causal Patch Interventions
di: Gupta, Manan, et al.
Pubblicazione: (2025)

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

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
di: Shu, Dong, et al.
Pubblicazione: (2025)

Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
di: Kopf, Laura, et al.
Pubblicazione: (2025)

Selective Neuron Amplification in Transformer Language Models
di: Akhtar, Ryyan, et al.
Pubblicazione: (2026)

Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
di: Shu, Dong, et al.
Pubblicazione: (2025)

Neuron-Level Knowledge Attribution in Large Language Models
di: Yu, Zeping, et al.
Pubblicazione: (2023)

Finding Culture-Sensitive Neurons in Vision-Language Models
di: Zhao, Xiutian, et al.
Pubblicazione: (2025)

Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation
di: Gu, Jian, et al.
Pubblicazione: (2023)

Learnable Privacy Neurons Localization in Language Models
di: Chen, Ruizhe, et al.
Pubblicazione: (2024)

Confidence Regulation Neurons in Language Models
di: Stolfo, Alessandro, et al.
Pubblicazione: (2024)

GLUScope: A Tool for Analyzing GLU Neurons in Transformer Language Models
di: Gerstner, Sebastian, et al.
Pubblicazione: (2026)

Improving Neuron-level Interpretability with White-box Language Models
di: Bai, Hao, et al.
Pubblicazione: (2024)

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models
di: Ali, Ameen, et al.
Pubblicazione: (2025)

Unveiling the Influence of Amplifying Language-Specific Neurons
di: Rahmanisa, Inaya, et al.
Pubblicazione: (2025)

Universal Neurons in GPT2 Language Models
di: Gurnee, Wes, et al.
Pubblicazione: (2024)

Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
di: Zhao, Haiyan, et al.
Pubblicazione: (2024)

Fine-Grained Interpretation of Political Opinions in Large Language Models
di: Hu, Jingyu, et al.
Pubblicazione: (2025)

SPIN: Sparsifying and Integrating Internal Neurons in Large Language Models for Text Classification
di: Jiao, Difan, et al.
Pubblicazione: (2023)

PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits
di: Dreyer, Maximilian, et al.
Pubblicazione: (2024)

Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities
di: Zhang, Junyan, et al.
Pubblicazione: (2025)

LawLLM: Law Large Language Model for the US Legal System
di: Shu, Dong, et al.
Pubblicazione: (2024)

Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution
di: Haider, Muhammad Umair, et al.
Pubblicazione: (2025)

Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning
di: Hu, Jingyu, et al.
Pubblicazione: (2024)

Rep2Text: Decoding Full Text from a Single LLM Token Representation
di: Zhao, Haiyan, et al.
Pubblicazione: (2025)

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
di: Kazemi, Hamid, et al.
Pubblicazione: (2026)

Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding
di: Zhu, Yunchang, et al.
Pubblicazione: (2023)

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
di: Pan, Birong, et al.
Pubblicazione: (2025)

Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination
di: Yang, Nakyeong, et al.
Pubblicazione: (2023)

Constructing Interpretable Features from Compositional Neuron Groups
di: Shafran, Or, et al.
Pubblicazione: (2025)

Language-specific Neurons Do Not Facilitate Cross-Lingual Transfer
di: Mondal, Soumen Kumar, et al.
Pubblicazione: (2025)

Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs
di: Liu, Jinzhe, et al.
Pubblicazione: (2025)

Polysemantic Experts, Monosemantic Paths: Routing as Control in MoEs
di: Ye, Charles, et al.
Pubblicazione: (2026)

Knowledge Graph Large Language Model (KG-LLM) for Link Prediction
di: Shu, Dong, et al.
Pubblicazione: (2024)

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models
di: Li, Zihao, et al.
Pubblicazione: (2025)