INDEX

Explanations

="

np_max-act · gemini-2.0-flash

The neuron is primarily detecting HTML/XML attribute assignments—that is, the `=` character immediately before an opening quotation mark for an attribute value.

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

-0.07

 Congo

-0.07

Nie

-0.07

 Vern

-0.06

/signup

-0.06

lat

-0.06

<>();↵

-0.06

FDA

-0.06

POSITIVE LOGITS

/posts

0.07

τύ

0.07

ynchronized

0.06

ricing

0.06

ama

0.06

 cout

0.06

azers

0.06

 procent

0.06

 convo

0.06

.isPresent

0.06

Activations Density 0.001%

="

The neuron is primarily detecting HTML/XML attribute assignments—that is, the `=` character immediately before an opening quotation mark for an attribute value.

No Comments

No Known Activations