© 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 · 56189 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
56189

INDEX

Explanations

i'd be

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

ogui

-0.10

Zub

-0.09

yh

-0.09

Pragma

-0.09

-0.09

uen

-0.08

’;d

-0.08

ï½Ŀ

-0.08

kyt

-0.08

-0.08

POSITIVE LOGITS

 pleasure

0.15

 happy

0.12

 rather

0.12

 plaisir

0.11

 Rather

0.11

 like

0.11

 love

0.11

happy

0.10

Happy

0.10

be

0.10

Activations Density 0.023%

No Known Activations