INDEX

Explanations

width

np_max-act · gemini-2.0-flash

The neuron is specialized to pick out HTML/XML tag delimiters (i.e. the “<…>” markup tokens).

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

.tabs

-0.06

requent

-0.06

DDS

-0.06

ods

-0.06

-num

-0.06

ITCH

-0.06

oling

-0.06

彦

-0.06

MOR

-0.06

Prev

-0.06

POSITIVE LOGITS

��

0.07

 электр

0.07

 boyut

0.06

 العربية

0.06

 adversely

0.06

.UN

0.06

WithName

0.06

 aload

0.06

 kullanımı

0.06

黑

0.06

Activations Density 0.013%

width

The neuron is specialized to pick out HTML/XML tag delimiters (i.e. the “<…>” markup tokens).

No Comments

No Known Activations