© 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 · 130375 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
130375

INDEX

Explanations

for

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

 comprom

-0.07

pheric

-0.07

&E

-0.06

án

-0.06

 많이

-0.06

iological

-0.06

 전용면적

-0.06

<String

-0.06

ocratic

-0.06

 halten

-0.06

POSITIVE LOGITS

hu

0.07

 audio

0.07

 Quant

0.07

MERCHANTABILITY

0.07

 Hess

0.06

yö

0.06

(ERR

0.06

 done

0.06

 newUser

0.06

 knex

0.06

Activations Density 0.021%

No Known Activations