INDEX

Explanations

dates

np_max-act · gemini-2.0-flash

The neuron fires on date tokens (month names and numeric parts of dates).

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

plings

-0.07

 crore

-0.07

reg

-0.06

ERICAN

-0.06

 mineral

-0.06

zburg

-0.06

Transformer

-0.06

्रब

-0.06

 transformer

-0.06

OPER

-0.06

POSITIVE LOGITS

 newsletter

0.06

 Proceed

0.06

 خصوص

0.06

	↵		↵

0.06

()}}↵

0.06

.estado

0.06

 руку

0.06

ADV

0.06

 Shadow

0.06

(Array

0.06

Activations Density 0.011%

dates

The neuron fires on date tokens (month names and numeric parts of dates).

No Comments

No Known Activations