© 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 · 77455 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
77455

INDEX

Explanations

irrational

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

บ

-0.07

 Nobody

-0.06

 πολυ

-0.06

 userAgent

-0.06

_quad

-0.06

 frontend

-0.06

-тех

-0.06

 =======

-0.06

hydro

-0.06

苹果

-0.06

POSITIVE LOGITS

leşme

0.07

 irrational

0.07

 سام

0.06

 sonic

0.06

ією

0.06

.AutoSize

0.06

zm

0.06

 Üç

0.06

 vữ

0.06

тю

0.06

Activations Density 0.002%

No Known Activations