© 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 · 117028 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
117028

INDEX

Explanations

code

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

_expand

-0.07

RESSION

-0.07

Face

-0.06

emento

-0.06

 progressive

-0.06

路

-0.06

เคล

-0.06

 Montana

-0.06

 sın

-0.06

�

-0.06

POSITIVE LOGITS

	Namespace

0.07

 Beds

0.07

.relu

0.06

!!.

0.06

 Goku

0.06

square

0.06

 Scots

0.06

çi

0.06

 innocence

0.06

lang

0.06

Activations Density 0.010%

No Known Activations