INDEX

Explanations

antiphospholipid syndrome

np_max-act · gemini-2.0-flash

The neuron detects occurrences of the substring “phospholipid” (as in “antiphospholipid syndrome”).

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

 cortisol

-0.06

_Cancel

-0.06

 introduce

-0.06

_notice

-0.06

/do

-0.06

마다

-0.06

 липня

-0.06

_wc

-0.06

 crippled

-0.06

paces

-0.06

POSITIVE LOGITS

ث

0.07

 Selenium

0.06

 positioned

0.06

 decorative

0.06

Ν

0.06

 Ні

0.06

IP

0.06

.getProperties

0.06

.tintColor

0.06

압

0.06

Activations Density 0.001%

antiphospholipid syndrome

The neuron detects occurrences of the substring “phospholipid” (as in “antiphospholipid syndrome”).

No Comments

No Known Activations

antiphospholipid syndrome

The neuron detects occurrences of the substring “phospholipid” (as in “antiphospholipid syndrome”).

No Comments

No Known Activations