conftrace_

internal activation

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (3) sparse autoencoder (2) model interpretability (2) pre-training detection (1) perplexity score (1) probing technique (1) arithmetic reasoning (1) knowledge conflict (1) inference-time intervention (1) llm alignment (1)

Papers

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Datasets Dependency ACL 2025 Probing for Arithmetic Errors in Language Models EMNLP 2025 SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals EMNLP 2025 Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering NAACL 2025 Token-Aware Editing of Internal Activations for Large Language Model Alignment EMNLP 2025 Probing Language Models for Pre-training Data Detection ACL 2024 Truth is Universal: Robust Detection of Lies in LLMs NeurIPS 2024 Discovering Latent Knowledge in Language Models Without Supervision ICLR 2023