INDEX

Explanations

importance

np_max-act · gemini-2.0-flash

the neuron detects words that signal importance or emphasis, such as “key,” “important,” or “major.”

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

 indoors

-0.07

 Aside

-0.07

 faculties

-0.07

義

-0.06

рім

-0.06

_TA

-0.06

 baik

-0.06

 upside

-0.06

 이러

-0.06

 systemic

-0.06

POSITIVE LOGITS

ookie

0.08

;")↵

0.07

"↵

0.07

察

0.07

 robe

0.07

"})↵

0.07

 ");↵

0.07

>}↵

0.06

 روان

0.06

 έκ

0.06

Activations Density 0.024%

importance

the neuron detects words that signal importance or emphasis, such as “key,” “important,” or “major.”

No Comments

No Known Activations

importance

the neuron detects words that signal importance or emphasis, such as “key,” “important,” or “major.”

No Comments

No Known Activations