INDEX

Explanations

find

np_max-act · gemini-2.0-flash

The neuron fires on occurrences of the verb “find.”

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

 uniquely

-0.07

yah

-0.07

owned

-0.07

 fully

-0.07

fd

-0.07

PMENT

-0.06

рован

-0.06

 prevention

-0.06

 will

-0.06

opt

-0.06

POSITIVE LOGITS

	Return

0.07

_FOLDER

0.06

 الشي

0.06

DivElement

0.06

"('

0.06

.ReadFile

0.06

引用频次

0.06

.Center

0.06

 založ

0.06

Activations Density 0.012%

find

The neuron fires on occurrences of the verb “find.”

No Comments

No Known Activations