INDEX

Explanations

Pat

np_max-act · gemini-2.0-flash

The neuron activates on tokens used in patent citations (e.g. “Pat.” and “U.S.” in “U.S. Pat. No. …”).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

technical specifications related to inventions and devices.

oai_token-act-pair · gpt-4o-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

ฤศจ

-0.07

(other

-0.07

 undermine

-0.06

�

-0.06

๊

-0.06

地球

-0.06

 tavern

-0.06

남도

-0.06

 reopened

-0.06

 reservations

-0.06

POSITIVE LOGITS

 **↵

0.07

0.06

cter

0.06

FIG

0.06

uti

0.06

.'),↵

0.06

 Active

0.06

 fiat

0.06

 Scientists

0.06

」↵↵

0.06

Activations Density 0.005%

Pat

The neuron activates on tokens used in patent citations (e.g. “Pat.” and “U.S.” in “U.S. Pat. No. …”).

technical specifications related to inventions and devices.

No Comments

No Known Activations