INDEX

Explanations

to

np_max-act · gemini-2.0-flash

The neuron is tuned to detect the discourse marker “in order to” (and its component tokens “in,” “order,” “to”) that introduces a purpose clause.

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

.setTo

-0.07

 fists

-0.06

.accept

-0.06

impse

-0.06

 ты

-0.06

 сайті

-0.06

(download

-0.06

 कह

-0.06

_glyph

-0.06

aktion

-0.05

POSITIVE LOGITS

_parameters

0.07

EncodingException

0.07

 Competitive

0.07

 woven

0.07

wed

0.07

 bağımsız

0.06

 Decorating

0.06

monkey

0.06

.getOwnProperty

0.06

Activations Density 0.019%

to

The neuron is tuned to detect the discourse marker “in order to” (and its component tokens “in,” “order,” “to”) that introduces a purpose clause.

No Comments

No Known Activations