INDEX

Explanations

flexible

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of the adjective “flexible” in technical or patent‐style text.

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

，说

-0.07

 Spells

-0.06

쳐

-0.06

 raid

-0.06

toString

-0.06

 eaten

-0.06

nah

-0.06

Out

-0.06

 НА

-0.06

POSITIVE LOGITS

 flexible

0.14

Flexible

0.11

 Flexible

0.10

 flexibility

0.10

_dual

0.09

 Flex

0.08

flex

0.08

"<?

0.07

mpg

0.07

 Fuse

0.07

Activations Density 0.009%

flexible

This neuron activates on occurrences of the adjective “flexible” in technical or patent‐style text.

No Comments

No Known Activations