© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 89934 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
89934

INDEX

Explanations

code/markup

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

'int

-0.07

onces

-0.06

gles

-0.06

Vis

-0.06

 step

-0.06

Modificar

-0.06

 откры

-0.06

assemble

-0.06

SER

-0.06

THB

-0.06

POSITIVE LOGITS

iy

0.07

Dating

0.07

ême

0.07

 rowCount

0.07

0.07

Browse

0.06

ุตสาห

0.06

(![

0.06

орт

0.06

Whether

0.06

Activations Density 0.000%

No Known Activations