© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 19-RESID-POST-AA · 112919 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
112919

INDEX

Explanations

il

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

 ότι

-0.06

Uz

-0.06

 camping

-0.06

 Phrase

-0.06

lanmış

-0.06

 Archived

-0.06

 trovare

-0.06

 unresolved

-0.06

 placement

-0.06

 Tempo

-0.06

POSITIVE LOGITS

il

0.11

ิลล

0.08

ils

0.08

IL

0.08

ila

0.08

ï

0.07

ill

0.07

ril

0.07

ILL

0.07

illi

0.07

Activations Density 0.038%

No Known Activations