INDEX

Explanations

but

np_max-act · gemini-2.0-flash

The neuron activates on contrastive or comparative cue words—little transition markers like “but,” “however,” “better,” etc.

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

Later

-0.07

рад

-0.07

Kir

-0.06

 effective

-0.06

_current

-0.06

Crow

-0.06

 Drink

-0.06

(DataType

-0.06

-ion

-0.06

 Font

-0.06

POSITIVE LOGITS

 Sır

0.07

 dès

0.07

ｌ

0.06

であ

0.06

vern

0.06

_extractor

0.06

キャ

0.06

WL

0.06

 serão

0.06

 Kasım

0.06

Activations Density 0.068%

but

The neuron activates on contrastive or comparative cue words—little transition markers like “but,” “however,” “better,” etc.

No Comments

No Known Activations