© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.3-70B-IT · 50-RESID-POST-GF · 41372 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
41372

INDEX

Explanations

first person

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

addy

-0.10

/*č\n

-0.10

 Coch

-0.09

ials

-0.09

/lg

-0.09

 Granny

-0.08

ihn

-0.08

-sided

-0.08

-door

-0.08

-volume

-0.08

POSITIVE LOGITS

aid

0.19

Aid

0.18

enberg

0.15

aid

0.15

 cousins

0.15

-rate

0.14

 aider

0.14

 timers

0.14

 baseman

0.14

 tiÃªn

0.14

Activations Density 0.055%

No Known Activations