© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 112895 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
112895

INDEX

Explanations

material removal

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

 بم

-0.07

orr

-0.06

 StringType

-0.06

 eBook

-0.06

-0.06

idx

-0.06

ौं

-0.06

alg

-0.06

 Babe

-0.06

 Tell

-0.06

POSITIVE LOGITS

 wearable

0.06

 utrecht

0.06

-child

0.06

扱

0.06

maları

0.06

dù

0.06

.ToDecimal

0.06

flex

0.06

한

0.06

otypes

0.06

Activations Density 0.028%

No Known Activations