INDEX

Explanations

code and markup

np_max-act · gemini-2.0-flash

This neuron activates on HTML table markup, especially the `<th>`, `<td>`, `<table>`, and related angle-bracket tags.

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

ちら

-0.07

цями

-0.06

 Transparent

-0.06

ації

-0.06

ệu

-0.06

еним

-0.06

عم

-0.06

仕事

-0.06

 gems

-0.06

 웹사이트

-0.06

POSITIVE LOGITS

_dyn

0.07

_parser

0.07

.wp

0.07

_vc

0.07

 Column

0.07

 COLUMN

0.07

repeat

0.06

 throttle

0.06

nrw

0.06

Activations Density 0.074%

code and markup

This neuron activates on HTML table markup, especially the `<th>`, `<td>`, `<table>`, and related angle-bracket tags.

No Comments

No Known Activations