INDEX

Explanations

some

np_max-act · gemini-2.0-flash

This neuron responds to vague, non-numeric quantifier words indicating an unspecified subset (e.g. “some,” “certain”).

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

Hour

-0.08

 fait

-0.07

ดาว

-0.07

Ю

-0.06

eně

-0.06

-use

-0.06

erts

-0.06

 burnt

-0.06

Song

-0.06

.charset

-0.06

POSITIVE LOGITS

ergic

0.07

.[

0.06

=False

0.06

 //----------------------------------------------------------------

0.06

creature

0.06

Rc

0.06

�

0.06

 propelled

0.06

MEP

0.06

(se

0.06

Activations Density 0.061%

some

This neuron responds to vague, non-numeric quantifier words indicating an unspecified subset (e.g. “some,” “certain”).

No Comments

No Known Activations