INDEX

Explanations

item

np_max-act · gemini-2.0-flash

This neuron activates on code tokens referring to retrieving items or item positions (e.g. getCheckedItemPositions, Item, Items).

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

 Alta

-0.07

dat

-0.06

lg

-0.06

Sem

-0.06

aines

-0.06

!");

-0.06

Eld

-0.06

Emma

-0.06

:↵↵↵↵↵↵

-0.06

oved

-0.06

POSITIVE LOGITS

.pair

0.07

 срок

0.07

.BigDecimal

0.07

("'"

0.06

 ROUND

0.06

\Persistence

0.06

�

0.06

币

0.06

 طریق

0.06

 부분

0.06

Activations Density 0.024%

item

This neuron activates on code tokens referring to retrieving items or item positions (e.g. getCheckedItemPositions, Item, Items).

No Comments

No Known Activations

item

This neuron activates on code tokens referring to retrieving items or item positions (e.g. getCheckedItemPositions, Item, Items).

No Comments

No Known Activations