© 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 · 20734 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
20734

INDEX

Explanations

Ke

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

↵

-0.08

udic

-0.07

 Famous

-0.07

atr

-0.07

_START

-0.07

compressed

-0.07

↵

-0.07

-reg

-0.06

 sync

-0.06

_oc

-0.06

POSITIVE LOGITS

0.07

 kéo

0.07

 Kane

0.07

 přibliž

0.06

Ke

0.06

 herald

0.06

 reporter

0.06

Pas

0.06

Deployment

0.06

ubbo

0.06

Activations Density 0.028%

No Known Activations