© 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 · 119859 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
119859

INDEX

Explanations

boots and shoes

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

ACING

-0.07

 komen

-0.07

_Total

-0.07

 accel

-0.06

 Пари

-0.06

ettel

-0.06

ovaných

-0.06

 Innov

-0.06

xad

-0.06

(delta

-0.06

POSITIVE LOGITS

 exercising

0.07

نس

0.07

ुँ

0.06

PreferredGap

0.06

 ergonomic

0.06

 الذي

0.06

 하나

0.06

 граждан

0.06

จำ

0.06

-support

0.06

Activations Density 0.006%

No Known Activations