INDEX

Explanations

Absent

np_max-act · gemini-2.0-flash

The neuron detects mentions of formal absence or attendance issues—words like “absent,” “absence,” and related terms in an excuse/attendance context.

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

igos

-0.07

Comput

-0.07

()-

-0.06

 promotional

-0.06

 tier

-0.06

Swipe

-0.06

 parseFloat

-0.06

 İyi

-0.06

Developer

-0.06

ret

-0.06

POSITIVE LOGITS

needle

0.07

lessons

0.06

omatic

0.06

 Alger

0.06

ﾊ

0.06

rbrace

0.06

 unheard

0.06

rene

0.06

だった

0.06

RAIN

0.06

Activations Density 0.016%

Absent

The neuron detects mentions of formal absence or attendance issues—words like “absent,” “absence,” and related terms in an excuse/attendance context.

No Comments

No Known Activations