© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 77688 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
77688

INDEX

Explanations

code selection/range

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

Models

-0.08

arcy

-0.07

_cov

-0.07

 Piano

-0.07

ція

-0.07

디어

-0.06

 kidneys

-0.06

arges

-0.06

 trend

-0.06

 Scatter

-0.06

POSITIVE LOGITS

党

0.07

以及

0.06

peng

0.06

 губ

0.06

 yüzyıl

0.06

<Scalar

0.06

0.06

 시작

0.06

.tele

0.06

<head

0.06

Activations Density 0.232%

No Known Activations