© 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 · 58308 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
58308

INDEX

Explanations

user behavior and marketing

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

.She

-0.07

onymous

-0.06

وح

-0.06

-0.06

ниць

-0.06

áh

-0.06

 мир

-0.06

звичай

-0.06

邮箱

-0.06

She

-0.06

POSITIVE LOGITS

 Vulkan

0.07

dig

0.07

 adaptation

0.06

ARI

0.06

0.06

 плав

0.06

 strand

0.06

ullet

0.06

,ev

0.06

BIND

0.06

Activations Density 0.023%

No Known Activations