© 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 · 7-RESID-POST-AA · 94179 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
94179

INDEX

Explanations

{

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

 ایجاد

-0.07

 tespit

-0.07

Crear

-0.07

 تغییر

-0.07

 fragile

-0.06

 LOCK

-0.06

 oleh

-0.06

 captive

-0.06

.put

-0.06

ديث

-0.06

POSITIVE LOGITS

0.07

acterial

0.07

ϊκ

0.06

	props

0.06

apellido

0.06

_Property

0.06

 Colorado

0.06

terrorism

0.06

_EXTRA

0.06

erk

0.06

Activations Density 0.001%

No Known Activations