INDEX

Explanations

plot

np_max-act · gemini-2.0-flash

This neuron activates on words referring to the structure of a narrative—e.g., “plot,” “events,” “storyline.”

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

/xhtml

-0.07

rvé

-0.07

♀♀

-0.06

ras

-0.06

 fishermen

-0.06

"`

-0.06

ierarchical

-0.06

sport

-0.06

 ragazzi

-0.06

ushort

-0.06

POSITIVE LOGITS

 plot

0.10

FAT

0.07

없

0.07

 moves

0.07

 loop

0.07

Drag

0.07

�

0.07

 Libya

0.07

 flavored

0.06

ops

0.06

Activations Density 0.007%

plot

This neuron activates on words referring to the structure of a narrative—e.g., “plot,” “events,” “storyline.”

No Comments

No Known Activations