Cover Image

Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Karvonen, Adam, Chua, James, Dumas, Clément, Fraser-Taliente, Kit, Kantamneni, Subhash, Minder, Julian, Ong, Euan, Sharma, Arnab Sen, Wen, Daniel, Evans, Owain, Marks, Samuel
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The $T^{μν}$ of the conformal scalars
by: Fraser-Taliente, Kit, et al.
Published: (2026)

Believe It or Not: How Deeply do LLMs Believe Implanted Facts?
by: Slocum, Stewart, et al.
Published: (2025)

The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious
by: Chua, James, et al.
Published: (2026)

Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences
by: Minder, Julian, et al.
Published: (2025)

Diffusion Models for Cayley Graphs
by: Douglas, Michael R., et al.
Published: (2025)

Language Models Use Trigonometry to Do Addition
by: Kantamneni, Subhash, et al.
Published: (2025)

Are DeepSeek R1 And Other Reasoning Models More Faithful?
by: Chua, James, et al.
Published: (2025)

Robustly Improving LLM Fairness in Realistic Settings via Interpretability
by: Karvonen, Adam, et al.
Published: (2025)

Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning
by: Minder, Julian, et al.
Published: (2025)

The sphere free energy of the vector models to order $1/N$
by: Fraser-Taliente, Ludo
Published: (2025)

Local CFTs extremise $F$
by: Fraser-Taliente, Ludo
Published: (2026)

Quantum field theories with many fields
by: Fraser-Taliente, Ludo
Published: (2026)

Not So Flat Metrics
by: Fraser-Taliente, Kit, et al.
Published: (2024)

Negation Neglect: When models fail to learn negations in training
by: Mayne, Harry, et al.
Published: (2026)

OptPDE: Discovering Novel Integrable Systems via AI-Human Collaboration
by: Kantamneni, Subhash, et al.
Published: (2024)

How Do Transformers "Do" Physics? Investigating the Simple Harmonic Oscillator
by: Kantamneni, Subhash, et al.
Published: (2024)

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs
by: Taylor, Mia, et al.
Published: (2025)

Symbolic Regression with Multimodal Large Language Models and Kolmogorov Arnold Networks
by: Harvey, Thomas R., et al.
Published: (2025)

$F$-extremization determines certain large-$N$ CFTs
by: Fraser-Taliente, Ludo, et al.
Published: (2024)

Melonic limits of the quartic Yukawa model and general features of melonic CFTs
by: Fraser-Taliente, Ludo, et al.
Published: (2024)

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
by: Treutlein, Johannes, et al.
Published: (2024)

Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
by: Chua, James, et al.
Published: (2025)

Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
by: Cloud, Alex, et al.
Published: (2025)

Scaling Laws For Scalable Oversight
by: Engels, Joshua, et al.
Published: (2025)

Tell me about yourself: LLMs are aware of their learned behaviors
by: Betley, Jan, et al.
Published: (2025)

Enumerating Calabi-Yau Manifolds: Placing bounds on the number of diffeomorphism classes in the Kreuzer-Skarke list
by: Chandra, Aditi, et al.
Published: (2023)

Computation of Quark Masses from String Theory
by: Constantin, Andrei, et al.
Published: (2024)

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks
by: Karvonen, Adam, et al.
Published: (2024)

Correlation Decay for Maximum Weight Matchings on Sparse Graphs
by: Lam, Wai-Kit, et al.
Published: (2025)

Central Limit Theorem in Disordered Monomer-Dimer Model
by: Lam, Wai-Kit, et al.
Published: (2022)

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

Fermion Masses and Mixing in String-Inspired Models
by: Constantin, Andrei, et al.
Published: (2024)

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
by: Kantamneni, Subhash, et al.
Published: (2025)

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
by: Betley, Jan, et al.
Published: (2025)

Efficient and Concise Explanations for Object Detection with Gaussian-Class Activation Mapping Explainer
by: Nguyen, Quoc Khanh, et al.
Published: (2024)

nnterp: A Standardized Interface for Mechanistic Interpretability of Transformers
by: Dumas, Clément
Published: (2025)

Resiliency and Reliability in the Cloud Engineering Era: Lessons from Strategy, Intelligence and AI
by: Kantamneni, Venkata Srinivas
Published: (2026)

A Nonlocal Schwinger Model
by: Fraser-Taliente, Ludovic, et al.
Published: (2024)

Data and the Decision-Making Process.
by: Minder, Thomas
Published: (1979)

Application of Systems Analysis in Designing a New System
by: Minder, Thomas
Published: (1973)