© 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

LLAMA3.1-8B-IT · 11-RESID-POST-AA · 51269 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
51269

INDEX

Explanations

|

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.Html

-0.07

 contempor

-0.07

_MULTI

-0.07

con

-0.07

bj

-0.06

unique

-0.06

_Inter

-0.06

 manoe

-0.06

	buff

-0.06

 Angry

-0.06

POSITIVE LOGITS

sell

0.06

 loaders

0.06

otes

0.06

 objedn

0.06

.nb

0.06

 LEFT

0.06

 Scientific

0.06

ellungen

0.06

Homepage

0.06

 phù

0.06

Activations Density 0.006%

No Known Activations