Daniel Scalena's picture

1 6 23

Daniel Scalena

DanielSc4

·

https://danielsc4.it

AI & ML interests

Safety and Interpretability

Recent Activity

updated a dataset about 5 hours ago

DanielSc4/alpaca-cleaned-italian

liked a model 5 days ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

liked a dataset 11 days ago

DanielSc4/alpaca-cleaned-italian

View all activity

Organizations

DanielSc4's activity

upvoted a collection about 1 month ago

EuroLLM

4 items • Updated Dec 2, 2024 • 25

upvoted a collection 3 months ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 15 items • Updated Dec 22, 2024 • 207

upvoted a paper 3 months ago

Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering

Paper • 2410.15999 • Published Oct 21, 2024 • 19

upvoted a paper 5 months ago

Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses

Paper • 2408.00584 • Published Aug 1, 2024 • 6

upvoted a paper 7 months ago

Multi-property Steering of Large Language Models with Dynamic Activation Composition

Paper • 2406.17563 • Published Jun 25, 2024 • 4

upvoted a collection about 1 year ago

🔍 Interpretability & Analysis of LMs

Outstanding research in LM interpretability and evaluation, summarized • 95 items • Updated 13 days ago • 96