© 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 · 34121 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
34121

INDEX

Explanations

sure

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

 cardiovascular

-0.06

_NAV

-0.06

alar

-0.06

Vari

-0.06

'(

-0.06

je

-0.06

interop

-0.06

ViewState

-0.06

Fro

-0.06

imas

-0.06

POSITIVE LOGITS

-pointer

0.07

_COMPAT

0.07

urge

0.06

 timestamps

0.06

）↵

0.06

 bites

0.06

src

0.06

 Rocks

0.06

-under

0.06

 late

0.06

Activations Density 0.006%

No Known Activations