© 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 · 87071 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
87071

INDEX

Explanations

math

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

Logo

-0.06

 atol

-0.06

类

-0.06

 económ

-0.06

BAM

-0.06

magnitude

-0.06

reflect

-0.06

 '/';↵

-0.06

 [],
↵

-0.06

reads

-0.06

POSITIVE LOGITS

,No

0.08

 Canucks

0.06

Occ

0.06

 gerade

0.06

Ca

0.06

 Betting

0.06

Iter

0.06

.imageView

0.06

 Escorts

0.06

EO

0.06

Activations Density 0.000%

No Known Activations