INDEX

Explanations

code snippets

np_max-act · gemini-2.0-flash

The neuron detects mentions of embedding or placing tracking/analytics code (e.g. JavaScript snippets) into a website’s HTML.

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

 terms

-0.07

 unsuccessful

-0.07

ительно

-0.07

yield

-0.07

IGH

-0.06

 Folding

-0.06

_fid

-0.06

рем

-0.06

_fx

-0.06

답

-0.06

POSITIVE LOGITS

AN

0.07

czas

0.07

lal

0.06

 padre

0.06

 hoop

0.06

 встре

0.06

 demonstrated

0.06

ektedir

0.06

 pornofilm

0.06

گز

0.06

Activations Density 0.050%

code snippets

The neuron detects mentions of embedding or placing tracking/analytics code (e.g. JavaScript snippets) into a website’s HTML.

No Comments

No Known Activations

code snippets

The neuron detects mentions of embedding or placing tracking/analytics code (e.g. JavaScript snippets) into a website’s HTML.

No Comments

No Known Activations