© 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 · 92250 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
92250

INDEX

Explanations

.js

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

 حمایت

-0.07

 PARAM

-0.06

.Conv

-0.06

 bilm

-0.06

.RequestParam

-0.06

 Qual

-0.06

 study

-0.06

 दव

-0.06

////////////////

-0.06

 aston

-0.06

POSITIVE LOGITS

Glass

0.08

-has

0.07

ोज

0.07

_IS

0.07

Ars

0.07

 HeaderComponent

0.07

GS

0.07

 Plans

0.07

罗斯

0.07

´s

0.07

Activations Density 0.015%

No Known Activations