INDEX

Explanations

quote

np_max-act · gemini-2.0-flash

This neuron activates on markers indicating quotations or quoted 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

_regions

-0.06

 areas

-0.06

 Snyder

-0.06

 cleaning

-0.06

 پایان

-0.06

 hive

-0.06

.testng

-0.06

 weary

-0.06

 indexPath

-0.06

 lifespan

-0.06

POSITIVE LOGITS

 quote

0.10

 quoting

0.10

Quote

0.09

 quotes

0.09

 quoted

0.08

OT

0.08

quoted

0.08

 quotation

0.08

quotes

0.08

quote

0.08

Activations Density 0.010%

quote

This neuron activates on markers indicating quotations or quoted text.

No Comments

No Known Activations