INDEX

Explanations

business and technology projects

np_max-act · gemini-2.0-flash

The neuron detects structural list or section markers—especially numbered headings and outline bullets.

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

 QCOMPARE

-0.07

Nah

-0.07

Inserted

-0.07

年

-0.07

 inhibition

-0.07

ueba

-0.06

 REALLY

-0.06

 infusion

-0.06

INES

-0.06

 свого

-0.06

POSITIVE LOGITS

useRal

0.06

);↵↵↵

0.06

_Project

0.06

컵

0.06

.bit

0.06

communic

0.06

shal

0.06

odox

0.05

checks

0.05

 limestone

0.05

Activations Density 0.099%

business and technology projects

The neuron detects structural list or section markers—especially numbered headings and outline bullets.

No Comments

No Known Activations

business and technology projects

The neuron detects structural list or section markers—especially numbered headings and outline bullets.

No Comments

No Known Activations