INDEX

Explanations

fin

np_max-act · gemini-2.0-flash

The neuron detects mentions of olefin (alkene) compounds, especially in contexts about olefin polymerization.

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

clock

-0.06

UpdatedAt

-0.06

 Gür

-0.06

енную

-0.06

Ket

-0.06

Т

-0.06

 Much

-0.06

사무

-0.06

ǎ

-0.06

 Buzz

-0.06

POSITIVE LOGITS

 dipped

0.07

 Expanded

0.07

crollView

0.07

Excellent

0.06

 italiani

0.06

 interpret

0.06

脸

0.06

่วน

0.06

 düşük

0.06

pub

0.06

Activations Density 0.001%

fin

The neuron detects mentions of olefin (alkene) compounds, especially in contexts about olefin polymerization.

No Comments

No Known Activations