INDEX

Explanations

sm

np_max-act · gemini-2.0-flash

sentiments associated with movie reviews, determining whether they are positive or negative.

oai_token-act-pair · gpt-4o-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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

buscar

-0.07

.scan

-0.07

 Belle

-0.06

ugar

-0.06

inema

-0.06

 parseFloat

-0.06

MS

-0.06

detect

-0.06

 сер

-0.06

 осіб

-0.06

POSITIVE LOGITS

/G

0.06

'nun

0.06

 Christmas

0.06

ThreadPool

0.06

 Declare

0.06

 después

0.06

 tranh

0.06

?“

0.06

าคาร

0.06

Tuy

0.06

Activations Density 0.014%

sm

sentiments associated with movie reviews, determining whether they are positive or negative.

No Comments

No Known Activations