© 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 · 92813 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
92813

INDEX

Explanations

the

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

Nombre

-0.07

 هنوز

-0.07

سد

-0.06

 tore

-0.06

 الناس

-0.06

ierrez

-0.06

 mọi

-0.06

uego

-0.06

 opcion

-0.06

LAN

-0.06

POSITIVE LOGITS

 skipped

0.07

 skip

0.07

 Skipping

0.07

smarty

0.06

.Handle

0.06

 Conduct

0.06

 skipping

0.06

 Communist

0.06

(of

0.06

Skipping

0.06

Activations Density 0.015%

No Known Activations