© 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 · 7-RESID-POST-AA · 47523 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
47523

INDEX

Explanations

considered

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

 VARIABLES

-0.07

 scrim

-0.07

-0.07

іон

-0.07

Wel

-0.07

willReturn

-0.07

є

-0.06

Yes

-0.06

 instrument

-0.06

Из

-0.06

POSITIVE LOGITS

iami

0.06

 midterm

0.06

ynchron

0.06

:::::::::::

0.06

 나타

0.06

 أحد

0.06

ych

0.06

fight

0.06

Warnings

0.05

wagon

0.05

Activations Density 0.026%

No Known Activations