© 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 · 86500 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
86500

INDEX

Explanations

CRISPR

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

话

-0.08

.task

-0.07

uvo

-0.07

 Gloss

-0.07

ilestone

-0.07

VH

-0.07

 losers

-0.06

_clicked

-0.06

 zinc

-0.06

的话

-0.06

POSITIVE LOGITS

PR

0.08

從

0.06

mpr

0.06

 byteArray

0.06

 Appro

0.06

.stride

0.06

velop

0.06

 arşiv

0.06

ugl

0.06

 họ

0.06

Activations Density 0.000%

No Known Activations