INDEX

Explanations

coding/language analysis

np_max-act · gemini-2.0-flash

This neuron fires on definite articles (e.g. “the” in English and “el/la/los/las” in Spanish) marking when a noun is being introduced as known or specific.

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

 permitted

-0.07

achts

-0.06

uder

-0.06

ườ

-0.06

ãng

-0.06

约

-0.06

erre

-0.06

าต

-0.06

 otáz

-0.06

atisation

-0.06

POSITIVE LOGITS

ά

0.07

 ipsum

0.07

aterangepicker

0.06

 compart

0.06

ui

0.06

 comma

0.06

__*/

0.06

.createStatement

0.06

escaping

0.06

 ordained

0.06

Activations Density 0.293%

coding/language analysis

This neuron fires on definite articles (e.g. “the” in English and “el/la/los/las” in Spanish) marking when a noun is being introduced as known or specific.

No Comments

No Known Activations