Cover Image

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Laptev, Daniil, Balagansky, Nikita, Aksenov, Yaroslav, Gavrilov, Daniil
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders
by: Kurochkin, Vadim, et al.
Published: (2025)

Teach Old SAEs New Domain Tricks with Boosting
by: Koriagin, Nikita, et al.
Published: (2025)

You Do Not Fully Utilize Transformer's Representation Capacity
by: Gerasimov, Gleb, et al.
Published: (2025)

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy
by: Balagansky, Nikita, et al.
Published: (2025)

Learn Your Reference Model for Real Good Alignment
by: Gorbatovski, Alexey, et al.
Published: (2024)

Linear Transformers with Learnable Kernel Functions are Better In-Context Models
by: Aksenov, Yaroslav, et al.
Published: (2024)

Diffusion Language Models Generation Can Be Halted Early
by: Vaina, Sofia Maria Lo Cicero, et al.
Published: (2023)

Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors
by: Sinii, Viacheslav, et al.
Published: (2025)

Mechanistic Permutability: Match Features Across Layers
by: Balagansky, Nikita, et al.
Published: (2024)

Next Embedding Prediction Makes World Models Stronger
by: Bredis, George, et al.
Published: (2026)

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

Trust-Region Behavior Blending for On-Policy Distillation
by: Plyusov, Daniil, et al.
Published: (2026)

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

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

Guided Star-Shaped Masked Diffusion
by: Meshchaninov, Viacheslav, et al.
Published: (2025)

Quantization of Large Language Models with an Overdetermined Basis
by: Merkulov, Daniil, et al.
Published: (2024)

Test Code Generation for Telecom Software Systems using Two-Stage Generative Model
by: Nabeel, Mohamad, et al.
Published: (2024)

nach0-pc: Multi-task Language Model with Molecular Point Cloud Encoder
by: Kuznetsov, Maksim, et al.
Published: (2024)

Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success
by: Bredis, George, et al.
Published: (2025)

Automatically Interpreting Millions of Features in Large Language Models
by: Paulo, Gonçalo, et al.
Published: (2024)

On Teacher Hacking in Language Model Distillation
by: Tiapkin, Daniil, et al.
Published: (2025)

DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning
by: Ignatev, Daniil, et al.
Published: (2025)

Crafting Large Language Models for Enhanced Interpretability
by: Sun, Chung-En, et al.
Published: (2024)

Steering Language Models with Weight Arithmetic
by: Fierro, Constanza, et al.
Published: (2025)

Steering Language Models With Activation Engineering
by: Turner, Alexander Matt, et al.
Published: (2023)

When an LLM is apprehensive about its answers -- and when its uncertainty is justified
by: Sychev, Petr, et al.
Published: (2025)

Complexity-aware fine-tuning
by: Goncharov, Andrey, et al.
Published: (2025)

Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models
by: Sundar, Anirudh, et al.
Published: (2025)

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
by: Jin, Zehao, et al.
Published: (2026)

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

Compositional Steering of Large Language Models with Steering Tokens
by: Radevski, Gorjan, et al.
Published: (2026)

Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models
by: Lan, Michael, et al.
Published: (2023)

Differentially Private Steering for Large Language Model Alignment
by: Goel, Anmol, et al.
Published: (2025)

Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
by: Cao, Yuanpu, et al.
Published: (2024)

EEFSUVA: A New Mathematical Olympiad Benchmark
by: Khatibi, Nicole N, et al.
Published: (2025)

Spherical Steering: Geometry-Aware Activation Rotation for Language Models
by: You, Zejia, et al.
Published: (2026)

Disentangling the Roles of Representation and Selection in Data Pruning
by: Du, Yupei, et al.
Published: (2025)

Superscopes: Amplifying Internal Feature Representations for Language Model Interpretation
by: Jacobi, Jonathan, et al.
Published: (2025)

Word Embeddings Are Steers for Language Models
by: Han, Chi, et al.
Published: (2023)

OpenAutoNLU: Open Source AutoML Library for NLU
by: Arshinov, Grigory, et al.
Published: (2026)