INDEX

Explanations

)

np_max-act · gemini-2.0-flash

The neuron detects section or subcategory headings in list-style documents (e.g. labels like “Drama series,” “Europe,” or “High schools”).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

formerly

-0.06

:test

-0.06

разу

-0.06

.Provider

-0.06

/latest

-0.06

Professor

-0.06

upakan

-0.06

инки

-0.06

MIC

-0.06

Tuple

-0.06

POSITIVE LOGITS

 페이지

0.07

 "-//

0.07

run

0.06

}:

0.06

 municipality

0.06

:::::::::::::::

0.06

.Btn

0.06

 violence

0.06

 standings

0.06

Activations Density 0.032%

)

The neuron detects section or subcategory headings in list-style documents (e.g. labels like “Drama series,” “Europe,” or “High schools”).

No Comments

No Known Activations