© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 127922 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
127922

INDEX

Explanations

at

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

 flat

-0.07

 prone

-0.07

entication

-0.06

MPH

-0.06

Scan

-0.06

 sponge

-0.06

Flow

-0.06

.entrySet

-0.06

 commune

-0.06

 lookout

-0.06

POSITIVE LOGITS

at

0.07

ара

0.07

аря

0.06

lda

0.06

الس

0.06

tí

0.06

 oversee

0.06

сих

0.06

РО

0.06

('$

0.06

Activations Density 0.075%

No Known Activations