© 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

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 20737 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
20737

INDEX

Explanations

of

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

�

-0.07

otal

-0.07

 NORMAL

-0.07

احة

-0.07

 Muslims

-0.06

 wider

-0.06

матрива

-0.06

 résult

-0.06

Round

-0.06

CR

-0.06

POSITIVE LOGITS

(Uri

0.06

_ENV

0.06

0.06

 развитие

0.06

Configurer

0.06

sĩ

0.06

rych

0.06

.CONFIG

0.06

_strlen

0.06

урн

0.06

Activations Density 0.213%

No Known Activations