INDEX

Explanations

of

np_max-act · gemini-2.0-flash

The neuron activates on words from Italian text, effectively detecting Italian-language tokens.

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

('%

-0.07

ousand

-0.07

 діяль

-0.06

Ele

-0.06

_waiting

-0.06

یط

-0.06

Microsoft

-0.06

arrings

-0.06

xbf

-0.06

POSITIVE LOGITS

Eş

0.07

 tack

0.06

合

0.06

Nur

0.06

opaque

0.06

prime

0.06

 voucher

0.06

 Taxi

0.06

vec

0.06

"""),↵

0.06

Activations Density 0.204%

of

The neuron activates on words from Italian text, effectively detecting Italian-language tokens.

No Comments

No Known Activations