© 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 · 19-RESID-POST-AA · 74036 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
74036

INDEX

Explanations

dignity and respect

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_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

طم

-0.07

 tart

-0.07

 BEFORE

-0.06

 edged

-0.06

(baseUrl

-0.06

jmp

-0.06

 mommy

-0.06

 elseif

-0.06

cdr

-0.06

$input

-0.06

POSITIVE LOGITS

 precondition

0.08

ertype

0.07

/std

0.06

offee

0.06

 pageNumber

0.06

uration

0.06

0.06

ubo

0.06

(IL

0.06

 dishes

0.06

Activations Density 0.073%

No Known Activations