© 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 · 27591 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
27591

INDEX

Explanations

my

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

angers

-0.07

module

-0.07

ACC

-0.06

;width

-0.06

gado

-0.06

 alice

-0.06

šit

-0.06

XH

-0.06

_CAT

-0.06

Sz

-0.06

POSITIVE LOGITS

 сохран

0.07

 свеж

0.06

 Saved

0.06

 перемен

0.06

0.06

 borderRadius

0.06

岡

0.06

iguiente

0.06

:]:↵

0.06

 보호

0.06

Activations Density 0.000%

No Known Activations