© 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 · 15-RESID-POST-AA · 58622 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
58622

INDEX

Explanations

Code/Programming

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

 друз

-0.07

と

-0.06

的大

-0.06

Cor

-0.06

 alcoholic

-0.06

Eig

-0.06

 ethnic

-0.06

 अब

-0.06

 will

-0.06

_allocation

-0.06

POSITIVE LOGITS

amm

0.08

Tam

0.07

][]

0.07

ада

0.06

(mem

0.06

esch

0.06

.house

0.06

랑스

0.06

emem

0.06

AAP

0.06

Activations Density 0.033%

No Known Activations