INDEX

Explanations

references to people and their relationships

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 often

-0.17

 Often

-0.15

Often

-0.14

oci

-0.14

atel

-0.14

ancy

-0.14

dbl

-0.14

Ã¤s

-0.13

çľł

-0.13

iets

-0.13

POSITIVE LOGITS

are

0.25

 aren

0.22

 weren

0.20

ptype

0.18

_are

0.18

 themselves

0.18

FRING

0.17

 were

0.17

 sÃ£o

0.17

 DÃ¼n

0.17

Activations Density 0.045%

references to people and their relationships

No Comments

No Known Activations