INDEX

Explanations

mc

np_max-act · gemini-2.0-flash

The neuron is picking out XML namespace declarations (xmlns:… attributes) in markup.

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

การจ

-0.07

准

-0.07

powers

-0.07

活動

-0.07

 servicios

-0.07

kovou

-0.06

 stavu

-0.06

☆

-0.06

cela

-0.06

 المح

-0.06

POSITIVE LOGITS

 Вики

0.07

-mar

0.06

_MM

0.06

 Crunch

0.06

 centrif

0.06

 Surrey

0.06

 cycl

0.06

Vim

0.06

iggs

0.06

metics

0.06

Activations Density 0.001%

mc

The neuron is picking out XML namespace declarations (xmlns:… attributes) in markup.

No Comments

No Known Activations