© 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 · 15-RESID-POST-AA · 20641 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
20641

INDEX

Explanations

numbers and symbols

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

-0.07

Accuracy

-0.06

 CompletableFuture

-0.06

PSU

-0.06

:i

-0.06

 compliment

-0.06

 Seminar

-0.06

uyu

-0.06

 elekt

-0.06

bit

-0.06

POSITIVE LOGITS

setText

0.07

inosaur

0.07

 Mercer

0.07

 Derek

0.06

성

0.06

影

0.06

 inhibitors

0.06

SEC

0.06

 เพราะ

0.06

duck

0.06

Activations Density 0.048%

No Known Activations