© 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 · 7670 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
7670

INDEX

Explanations

writ

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

 sanctioned

-0.07

 Mongo

-0.07

 normalize

-0.07

 efekt

-0.07

 foil

-0.07

 géné

-0.07

’e

-0.07

 menos

-0.07

 manufactures

-0.06

deny

-0.06

POSITIVE LOGITS

 writ

0.11

wt

0.07

 renovations

0.06

uti

0.06

식을

0.06

0.06

 Fransa

0.06

addItem

0.06

_RD

0.06

mutation

0.06

Activations Density 0.001%

No Known Activations