© 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 · 7-RESID-POST-AA · 92749 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
92749

INDEX

Explanations

get

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

dx

-0.06

Cha

-0.06

 modes

-0.06

ضو

-0.06

.green

-0.06

stvo

-0.06

ुह

-0.06

نا

-0.06

ör

-0.06

トル

-0.06

POSITIVE LOGITS

=output

0.06

ational

0.06

.StatusInternalServerError

0.06

-unstyled

0.06

.AddListener

0.06

onna

0.06

assic

0.06

 Velvet

0.06

iments

0.06

 όλ

0.06

Activations Density 0.022%

No Known Activations