INDEX

Explanations

incl

np_max-act · gemini-2.0-flash

This neuron specifically detects the Spanish word “incluyendo” (the gerund “including”), as shown by its strong activation on the “incl”/“uy” sub-tokens.

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

information related to programming languages and their frameworks.

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

Gene

-0.08

Ben

-0.07

 Hamilton

-0.07

欢

-0.07

 какие

-0.07

 Rape

-0.07

earer

-0.07

@@@@

-0.07

Regs

-0.07

"My

-0.07

POSITIVE LOGITS

 incl

0.07

CSS

0.07

(cl

0.07

<li

0.06

.getIndex

0.06

 sensual

0.06

 admitted

0.06

 getConfig

0.06

 nebu

0.06

 zastav

0.06

Activations Density 0.006%

incl

This neuron specifically detects the Spanish word “incluyendo” (the gerund “including”), as shown by its strong activation on the “incl”/“uy” sub-tokens.

information related to programming languages and their frameworks.

No Comments

No Known Activations