© 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 · 21257 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
21257

INDEX

Explanations

quantifiers

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

ä¸Ģç§į

-0.09

ä¸ĢçĤ¹

-0.09

 decades

-0.09

 DÃŃky

-0.09

arus

-0.09

vari

-0.09

 most

-0.08

_HC

-0.08

oust

-0.08

Injected

-0.08

POSITIVE LOGITS

/all

0.19

of

0.18

ones

0.17

place

0.16

/m

0.13

 things

0.11

-handed

0.10

 ihrer

0.10

 cool

0.10

ht

0.10

Activations Density 0.094%

No Known Activations