INDEX

Explanations

PT

np_max-act · gemini-2.0-flash

The neuron activates on mentions of the U.S. Patent and Trademark Office (USPTO) or related patent‐office terminology and abbreviations.

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

.No

-0.07

igated

-0.06

Thought

-0.06

 respondsToSelector

-0.06

Layers

-0.06

illas

-0.06

_PARAMS

-0.06

Rub

-0.06

ився

-0.06

函数

-0.06

POSITIVE LOGITS

lze

0.07

.hs

0.07

候

0.06

cheduling

0.06

атегор

0.06

$path

0.06

)();↵

0.06

 मई

0.06

 recognizes

0.06

 $("#"

0.06

Activations Density 0.004%

PT

The neuron activates on mentions of the U.S. Patent and Trademark Office (USPTO) or related patent‐office terminology and abbreviations.

No Comments

No Known Activations