© 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 · 27-RESID-POST-AA · 9623 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
9623

INDEX

Explanations

shell

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.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

 Better

-0.07

Save

-0.07

 granddaughter

-0.07

 safer

-0.06

 Fragment

-0.06

 diminished

-0.06

Dark

-0.06

 expres

-0.06

 riot

-0.06

 Dark

-0.06

POSITIVE LOGITS

 shell

0.10

Shell

0.09

 Shell

0.09

 shells

0.08

용

0.08

сыл

0.07

 Bone

0.07

shell

0.07

руб

0.07

 Morg

0.07

Activations Density 0.007%

No Known Activations