INDEX

Explanations

quotation marks

np_max-act · gemini-2.0-flash

This neuron activates on instances of the double-quote character (“) in the text.

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

ण

-0.07

riends

-0.07

Bec

-0.06

 attentive

-0.06

xBA

-0.06

 Interrupt

-0.06

Gio

-0.06

 paris

-0.06

 Lover

-0.06

throp

-0.06

POSITIVE LOGITS

 بود

0.07

ublik

0.06

 subsidiaries

0.06

 정말

0.06

 kendisine

0.06

pector

0.06

_ENABLED

0.06

 وكان

0.06

 अपन

0.06

 Except

0.06

Activations Density 0.041%

quotation marks

This neuron activates on instances of the double-quote character (“) in the text.

No Comments

No Known Activations