INDEX

Explanations

organic

np_max-act · gemini-2.0-flash

The neuron detects occurrences of the word “organic.”

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

 childs

-0.06

EXP

-0.06

 sett

-0.06

しまった

-0.06

 dostan

-0.06

 compatibility

-0.06

 Flood

-0.06

 dice

-0.06

だな

-0.06

ализ

-0.06

POSITIVE LOGITS

__(

0.07

.sendKeys

0.07

Ag

0.07

")]↵

0.07

マン

0.07

(dw

0.06

โรงแรม

0.06

漫画

0.06

Boom

0.06

 Bugün

0.06

Activations Density 0.001%

organic

The neuron detects occurrences of the word “organic.”

No Comments

No Known Activations