© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.3-70B-IT · 50-RESID-POST-GF · 62190 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
62190

INDEX

Explanations

a good idea

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf

Configuration

Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 marked

-0.09

insi

-0.09

-0.09

kla

-0.09

Margin

-0.09

utz

-0.08

 Favor

-0.08

 Morav

-0.08

apons

-0.08

boo

-0.08

POSITIVE LOGITS

 good

0.36

 idea

0.27

good

0.24

 gute

0.21

å¥½

0.20

idea

0.20

 buena

0.20

 ÑħÐ¾ÑĢÐ¾ÑĪ

0.19

iyi

0.19

 tá»ĳt

0.18

Activations Density 0.007%

No Known Activations