INDEX

Explanations

beer head

np_max-act · gemini-2.0-flash

This neuron activates on words describing a beer’s visual appearance—its pour, color, head, and foam characteristics.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵

-0.07

.*↵↵

-0.07

置

-0.07

 adamant

-0.06

Jeff

-0.06

 ruins

-0.06

MB

-0.06

jší

-0.06

==========

-0.06

zx

-0.06

POSITIVE LOGITS

 أي

0.07

forcements

0.07

allee

0.07

έργ

0.06

 Structures

0.06

 عليه

0.06

MSP

0.06

 держав

0.06

 Percent

0.06

otted

0.06

Activations Density 0.002%

beer head

This neuron activates on words describing a beer’s visual appearance—its pour, color, head, and foam characteristics.

No Comments

No Known Activations