INDEX

Explanations

shift

np_max-act · gemini-2.0-flash

The neuron activates on mentions of the Shift key (or shift‐modifier) in UI or code contexts (e.g. Shift+Click, Shift+Wheel, event.shiftKey).

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

料

-0.07

 multicast

-0.06

ore

-0.06

ció

-0.06

 Interpreter

-0.06

쪽

-0.06

озя

-0.06

ポ

-0.06

 отвер

-0.06

Tam

-0.06

POSITIVE LOGITS

яет

0.07

 Moving

0.06

hopefully

0.06

 submerged

0.06

>;↵↵

0.06

.Stream

0.06

 SUCH

0.06

 CLICK

0.06

 Battle

0.06

`<

0.06

Activations Density 0.003%

shift

The neuron activates on mentions of the Shift key (or shift‐modifier) in UI or code contexts (e.g. Shift+Click, Shift+Wheel, event.shiftKey).

No Comments

No Known Activations

shift

The neuron activates on mentions of the Shift key (or shift‐modifier) in UI or code contexts (e.g. Shift+Click, Shift+Wheel, event.shiftKey).

No Comments

No Known Activations