© 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 · 12467 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
12467

INDEX

Explanations

break after

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

 peaceful

-0.11

 Deng

-0.11

 open

-0.10

èĩ¨

-0.10

 peace

-0.09

SP

-0.09

 ï½²

-0.09

 borrowing

-0.09

 Bach

-0.09

 Peace

-0.09

POSITIVE LOGITS

 rest

0.17

 breaks

0.15

 Break

0.14

 break

0.13

/rest

0.12

ä¼ĳ

0.12

 rests

0.12

break

0.11

(rest

0.11

rest

0.11

Activations Density 0.020%

No Known Activations