© 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 · 73496 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
73496

INDEX

Explanations

has

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

 deren

-0.06

ə

-0.06

 widespread

-0.06

 Manuel

-0.06

PathParam

-0.06

Op

-0.06

UBL

-0.06

_seq

-0.06

altung

-0.06

bq

-0.06

POSITIVE LOGITS

 antagon

0.07

 Kiev

0.07

�

0.07

 auditor

0.06

 Soros

0.06

 Tehran

0.06

-major

0.06

 natural

0.06

 Swan

0.06

 точки

0.06

Activations Density 0.000%

No Known Activations