INDEX

Explanations

cytokines and inflammation

np_max-act · gemini-2.0-flash

The neuron consistently activates on the term “cytokine” (including its split‐up subtoken forms), i.e. mentions of cytokines.

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

-0.07

 metast

-0.07

 Bund

-0.07

 marriages

-0.07

 Malta

-0.06

PhD

-0.06

 leur

-0.06

 seront

-0.06

 spotřeb

-0.06

xaa

-0.06

POSITIVE LOGITS

$num

0.08

/inet

0.07

’in

0.07

เย

0.07

vine

0.07

 GUIDATA

0.07

 climbing

0.06

.openConnection

0.06

 TInt

0.06

ine

0.06

Activations Density 0.005%

cytokines and inflammation

The neuron consistently activates on the term “cytokine” (including its split‐up subtoken forms), i.e. mentions of cytokines.

No Comments

No Known Activations