INDEX

Explanations

punctuation

np_max-act · gemini-2.0-flash

The neuron fires on descriptive, “adjective-style” tokens (e.g. “Exquisite,” “acclaimed,” “Stunning,” etc.), flagging words that specify vivid qualities or attributes.

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

vat

-0.07

gt

-0.07

 github

-0.06

trim

-0.06

vom

-0.06

UIView

-0.06

_go

-0.06

 crimes

-0.06

_gui

-0.06

-cigarettes

-0.06

POSITIVE LOGITS

 toppings

0.07

 ViewGroup

0.06

 maken

0.06

(tableName

0.06

 greatly

0.06

 towns

0.06

 incontri

0.06

anything

0.06

 extensively

0.06

 belirlen

0.06

Activations Density 0.022%

punctuation

The neuron fires on descriptive, “adjective-style” tokens (e.g. “Exquisite,” “acclaimed,” “Stunning,” etc.), flagging words that specify vivid qualities or attributes.

No Comments

No Known Activations