© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

LLAMA3.3-70B-IT · 50-RESID-POST-GF · 45396 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
45396

INDEX

Explanations

being or to 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

sov

-0.11

abei

-0.10

rench

-0.09

inea

-0.09

ê°Ĳ

-0.08

 Warren

-0.08

 dÃ©couvrir

-0.08

-0.08

heit

-0.08

utan

-0.08

POSITIVE LOGITS

 byÄĩ

0.27

 essere

0.26

 bÃ½t

0.26

 Ãªtre

0.25

 Ð±ÑĭÑĤÑĮ

0.25

 being

0.25

è¢«

0.20

'Ãªtre

0.19

being

0.18

Ãªtre

0.18

Activations Density 0.097%

No Known Activations