© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 19-RESID-POST-AA · 99770 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
19-RESID-POST-AA
99770

INDEX

Explanations

must

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

Directed

-0.06

ceived

-0.06

 solved

-0.06

 Therefore

-0.06

 templ

-0.06

iddi

-0.06

 Rate

-0.06

ética

-0.06

 herein

-0.06

ays

-0.06

POSITIVE LOGITS

Ş

0.07

�

0.07

 REQUIRE

0.07

«

0.06

ég

0.06

‌دان

0.06

ائق

0.06

 chảy

0.06

uu

0.06

 طلب

0.06

Activations Density 0.039%

No Known Activations