© 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 · 46895 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
46895

INDEX

Explanations

Numbers

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

YYY

-0.07

-Shirt

-0.06

-0.06

(fields

-0.06

.func

-0.06

 menor

-0.06

eno

-0.06

-entity

-0.06

-stream

-0.06

 escapes

-0.05

POSITIVE LOGITS

 poke

0.07

ž

0.07

_SCHEDULE

0.07

 Cabin

0.07

 tarn

0.07

 unlaw

0.06

 مب

0.06

训

0.06

ños

0.06

 sık

0.06

Activations Density 0.015%

No Known Activations