© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 24096 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
24096

INDEX

Explanations

improvement

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

 stormed

-0.06

 systemic

-0.06

hits

-0.06

 Opportunities

-0.06

 Keep

-0.06

CLUSION

-0.06

름

-0.06

쓰

-0.06

그

-0.06

 battery

-0.06

POSITIVE LOGITS

/math

0.07

 slož

0.07

 setAddress

0.07

컨

0.07

 قن

0.07

Chr

0.06

 })),↵

0.06

.children

0.06

 tailor

0.06

/fr

0.06

Activations Density 0.024%

No Known Activations