INDEX

Explanations

enum

np_max-act · gemini-2.0-flash

The neuron detects hyperlink definitions in code—specifically the “links” and “href” keys indicating URI references.

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

 ناب

-0.07

 Cous

-0.07

 Lantern

-0.07

Collapsed

-0.07

 Projects

-0.07

strong

-0.07

 गय

-0.07

formace

-0.07

(Collectors

-0.07

 alone

-0.07

POSITIVE LOGITS

 impending

0.06

 درون

0.06

χο

0.06

Ill

0.06

 possessing

0.05

Hu

0.05

ựa

0.05

WR

0.05

hu

0.05

Coll

0.05

Activations Density 0.005%

enum

The neuron detects hyperlink definitions in code—specifically the “links” and “href” keys indicating URI references.

No Comments

No Known Activations