© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 46353 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
46353

INDEX

Explanations

::

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

 Dispatcher

-0.07

 kontakt

-0.06

JV

-0.06

 amphib

-0.06

 prev

-0.06

 खड

-0.06

 Пав

-0.06

-al

-0.06

 querying

-0.06

 lâu

-0.06

POSITIVE LOGITS

 предполаг

0.07

 некоторых

0.07

 Angelo

0.07

DI

0.07

0.06

TouchUpInside

0.06

pom

0.06

.raw

0.06

_dd

0.06

DlgItem

0.06

Activations Density 0.002%

No Known Activations