© 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 · 27-RESID-POST-AA · 22355 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
22355

INDEX

Explanations

answering questions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.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

 Correct

-0.07

Coordinates

-0.06

 dent

-0.06

extension

-0.06

.Ext

-0.06

інки

-0.06

-0.06

τεύ

-0.06

ød

-0.06

Setup

-0.06

POSITIVE LOGITS

	fflush

0.06

testdata

0.06

 fwrite

0.06

Ar

0.06

 doen

0.06

ning

0.06

 IMPLIED

0.05

 managed

0.05

_tile

0.05

 RAND

0.05

Activations Density 0.179%

No Known Activations