INDEX

Explanations

the

np_max-act · gemini-2.0-flash

The neuron is essentially picking out floating‐point numeric tokens (i.e. numbers with decimal points) in the 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sensual

-0.07

 Political

-0.07

urity

-0.07

 polish

-0.07

nef

-0.07

 tweaks

-0.06

Sink

-0.06

 businesses

-0.06

 Escape

-0.06

 joker

-0.06

POSITIVE LOGITS

china

0.06

ением

0.06

 ""));↵

0.06

概

0.06

"}}>↵

0.06

風

0.06

ué

0.06

 wang

0.06

 dijo

0.06

);">↵

0.06

Activations Density 0.067%

the

The neuron is essentially picking out floating‐point numeric tokens (i.e. numbers with decimal points) in the text.

No Comments

No Known Activations