INDEX

Explanations

text snippets

np_max-act · gemini-2.0-flash

The neuron consistently activates on French second‐person plural pronouns (e.g. “vos”).

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

 ва

-0.07

.lv

-0.06

shr

-0.06

kle

-0.06

uştur

-0.06

 fout

-0.06

κο

-0.06

 Niger

-0.06

ensored

-0.06

feed

-0.06

POSITIVE LOGITS

_LIGHT

0.07

ilename

0.06

HashCode

0.06

↵

0.06

Transaction

0.06

 появ

0.06

-License

0.06

navbar

0.06

 lược

0.06

 구성

0.06

Activations Density 0.045%

text snippets

The neuron consistently activates on French second‐person plural pronouns (e.g. “vos”).

No Comments

No Known Activations

text snippets

The neuron consistently activates on French second‐person plural pronouns (e.g. “vos”).

No Comments

No Known Activations