INDEX

Explanations

phrases indicating passive voice

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post

Features

65,536

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

gated

Context Size

1,024

Dataset

Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 disappe

-0.16

 HÃ¼s

-0.16

osloven

-0.16

EditingStyle

-0.16

quil

-0.15

AFX

-0.15

 Ð¿Ð¾Ð±Ð°

-0.15

 ilet

-0.15

ControlItem

-0.15

stanov

-0.14

POSITIVE LOGITS

 virtue

0.38

 means

0.33

 dint

0.26

gone

0.24

-products

0.24

the

0.23

 default

0.23

ron

0.22

products

0.22

Activations Density 0.178%

phrases indicating passive voice

No Comments

No Known Activations