© 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 · 33789 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
33789

INDEX

Explanations

fty

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

sheet

-0.06

 harmless

-0.06

belongsTo

-0.06

пе

-0.06

ISTR

-0.06

дяки

-0.06

_qos

-0.06

 favorable

-0.06

.rawValue

-0.06

isicing

-0.06

POSITIVE LOGITS

_license

0.07

://

0.06

 Mutation

0.06

 Worker

0.06

0.06

Ear

0.06

 Bridge

0.06

cdecl

0.06

 Vacation

0.06

DLL

0.06

Activations Density 0.000%

No Known Activations