© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 86424 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
86424

INDEX

Explanations

Beer

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

 mohou

-0.07

้ไข

-0.07

(Initialized

-0.07

ジュ

-0.07

رك

-0.06

ypsy

-0.06

 troublesome

-0.06

Conditions

-0.06

antic

-0.06

thic

-0.06

POSITIVE LOGITS

 beer

0.17

 Beer

0.13

Beer

0.11

 beers

0.11

beer

0.08

 امتی

0.08

agner

0.07

 Miller

0.07

 Wagner

0.07

	byte

0.07

Activations Density 0.004%

No Known Activations