© 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 · 36706 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
36706

INDEX

Explanations

across

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

εφ

-0.07

 goto

-0.07

 gimm

-0.07

ocolate

-0.07

-0.07

 MyBase

-0.07

afone

-0.07

KN

-0.06

probability

-0.06

GLISH

-0.06

POSITIVE LOGITS

 Renew

0.06

NM

0.06

すべて

0.06

.SH

0.05

-profit

0.05

 critics

0.05

que

0.05

ROLS

0.05

Lastly

0.05

Res

0.05

Activations Density 0.065%

No Known Activations