Gabriele Sarti

gsarti's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 2 days ago

Tracing Agentic Failure from the Flow of Success

Paper • 2607.12747 • Published 5 days ago • 14

upvoted an article 4 days ago

view article

Article

J-Space: Yet Another LLM Mind Reader?

• 

dlouapre

•

6 days ago

• 31

upvoted a paper 12 days ago

PACE: A Proxy for Agentic Capability Evaluation

Paper • 2607.02032 • Published 17 days ago • 18

upvoted a paper 15 days ago

Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads

Paper • 2607.01002 • Published 18 days ago • 19

upvoted a paper about 1 month ago

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models

Paper • 2605.11887 • Published May 12 • 18

upvoted a collection about 1 month ago

Qwen-Scope

Collection

16 items • Updated May 14 • 75

upvoted a paper about 2 months ago

Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth

Paper • 2605.25052 • Published May 24 • 14

upvoted 3 collections 3 months ago

1930 Coder

Collection

Fine-tuning the Talkie 13B 1930 model on agentic trajectories • 4 items • Updated May 5 • 4

DeepSeek-V4

Collection

6 items • Updated 22 days ago • 742

(Some) Emergent Misalignment from Reward Hacking in RL

Collection

Model checkpoints from the project "(Some) Natural Emergent Misalignment from Reward Hacking in Non-Production RL" • 228 items • Updated 18 days ago • 6

upvoted a collection 5 months ago

Qwen3.5

Collection

21 items • Updated Mar 9 • 1.72k

upvoted 3 papers 5 months ago

A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents

Paper • 2602.08964 • Published Feb 9 • 1

Agents of Chaos

Paper • 2602.20021 • Published Feb 23 • 36

Faithful Persona-based Conversational Dataset Generation with Large Language Models

Paper • 2312.10007 • Published Dec 15, 2023 • 11

upvoted 2 papers 6 months ago

Language Models Change Facts Based on the Way You Talk

Paper • 2507.14238 • Published Jul 17, 2025 • 1

Demographic Probing of Large Language Models Lacks Construct Validity

Paper • 2601.18486 • Published Jan 26 • 1

upvoted an article 6 months ago

view article

Article

🪄 Interpreto: A Unified Toolkit for Interpretability of Transformer Models

• 

Fannyjrd

•

Jan 20

• 39

upvoted a collection 7 months ago

Activation Oracles

Collection

12 items • Updated Dec 26, 2025 • 20

upvoted a paper 7 months ago

GIM: Improved Interpretability for Large Language Models

Paper • 2505.17630 • Published May 23, 2025 • 1

upvoted a collection 7 months ago

Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability

Collection

A compilation of sparse auto-encoders trained on large language models. • 37 items • Updated Dec 16, 2025 • 24