INDEX

Explanations

setting

np_max-act · gemini-2.0-flash

This neuron primarily activates on floating-point numeric tokens (decimal numbers).

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

 jump

-0.07

';'

-0.07

 prove

-0.06

 crawl

-0.06

 machine

-0.06

Hero

-0.06

 elephants

-0.06

ho

-0.06

 STANDARD

-0.06

POSITIVE LOGITS

 Sandbox

0.08

 setting

0.08

 intimidating

0.08

тур

0.07

Jur

0.07

직

0.07

 settings

0.07

 Forum

0.07

 Licensing

0.06

pretty

0.06

Activations Density 0.024%

setting

This neuron primarily activates on floating-point numeric tokens (decimal numbers).

No Comments

No Known Activations