© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 34559 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
34559

INDEX

Explanations

fee

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

ToJson

-0.07

랑스

-0.07

.easy

-0.06

uncated

-0.06

никами

-0.06

рити

-0.06

_tf

-0.06

SSD

-0.06

iếu

-0.06

 diplom

-0.06

POSITIVE LOGITS

 pleasures

0.06

 DevComponents

0.06

:self

0.06

vip

0.06

 حل

0.06

ál

0.06

(evt

0.06

्वप

0.06

het

0.06

='".

0.06

Activations Density 0.002%

No Known Activations