INDEX

Explanations

freemasonry

np_max-act · gemini-2.0-flash

The neuron selectively activates on Freemasonry–related terms (e.g. “masonic,” “Rite,” “Masonry,” “board”)—i.e. it detects Masonic jargon.

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

cete

-0.07

('#

-0.06

Lew

-0.06

 فقط

-0.06

 subconscious

-0.06

	UFUNCTION

-0.06

("#

-0.06

 Magnus

-0.06

 parking

-0.06

)'),↵

-0.06

POSITIVE LOGITS

 edin

0.08

 gastro

0.07

 modified

0.07

 ingres

0.07

_SUCCESS

0.07

 Freem

0.06

 sympt

0.06

endpoint

0.06

 precaution

0.06

 affordability

0.06

Activations Density 0.008%

freemasonry

The neuron selectively activates on Freemasonry–related terms (e.g. “masonic,” “Rite,” “Masonry,” “board”)—i.e. it detects Masonic jargon.

No Comments

No Known Activations

freemasonry

The neuron selectively activates on Freemasonry–related terms (e.g. “masonic,” “Rite,” “Masonry,” “board”)—i.e. it detects Masonic jargon.

No Comments

No Known Activations