INDEX

Explanations

finite

np_max-act · gemini-2.0-flash

This neuron activates specifically on the word “finite.”

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

Availability

-0.07

_rooms

-0.07

 Coastal

-0.06

icrobial

-0.06

 Painter

-0.06

Cou

-0.06

 Mozart

-0.06

 youngsters

-0.06

iedad

-0.06

mor

-0.06

POSITIVE LOGITS

toLocale

0.06

 =↵

0.06

 insn

0.06

!(

0.06

/*!↵

0.06

 صنعتی

0.06

 Holland

0.06

slideDown

0.06

.RowIndex

0.06

Uma

0.06

Activations Density 0.003%

finite

This neuron activates specifically on the word “finite.”

No Comments

No Known Activations

finite

This neuron activates specifically on the word “finite.”

No Comments

No Known Activations