INDEX

Explanations

et

np_max-act · gemini-2.0-flash

specific dates and announcements related to events or transactions.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

The neuron activates on individual named‐entity tokens—proper nouns, acronyms, and other capitalized identifiers.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uncture

-0.07

éru

-0.07

 příslu

-0.06

 Understand

-0.06

 sentir

-0.06

錯

-0.06

Hi

-0.06

 foyer

-0.06

 acknowledging

-0.06

 Hers

-0.06

POSITIVE LOGITS

 Maple

0.07

’l

0.06

лом

0.06

.Class

0.06

CharArray

0.06

Menus

0.06

_Test

0.06

 gifted

0.06

Berry

0.06

Activations Density 0.268%

et

specific dates and announcements related to events or transactions.

The neuron activates on individual named‐entity tokens—proper nouns, acronyms, and other capitalized identifiers.

No Comments

No Known Activations