INDEX

Explanations

vaccine

np_max-act · gemini-2.0-flash

The neuron detects statements indicating the absence or unavailability of vaccines or specific treatments.

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

chner

-0.07

Kay

-0.07

Eck

-0.07

enské

-0.07

 věku

-0.06

 getPrice

-0.06

/");↵

-0.06

 pizzas

-0.06

 nephew

-0.06

figures

-0.06

POSITIVE LOGITS

_PARTITION

0.07

 Spreadsheet

0.07

(trans

0.07

CA

0.06

 पहच

0.06

_chunks

0.06

 dimin

0.06

SWEP

0.06

nerRadius

0.06

.defaultProps

0.06

Activations Density 0.018%

vaccine

The neuron detects statements indicating the absence or unavailability of vaccines or specific treatments.

No Comments

No Known Activations