INDEX

Explanations

mentions of soccer teams and players

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

å¤®

-0.16

ipl

-0.15

_TM

-0.15

odate

-0.14

olist

-0.14

avn

-0.14

à¹Īà¸Ńà¸ĩ

-0.14

keit

-0.14

eday

-0.14

POSITIVE LOGITS

 star

0.29

man

0.23

 bound

0.20

star

0.20

ace

0.20

 legend

0.20

 stars

0.19

-bound

0.19

duo

0.18

 reject

0.18

Activations Density 0.041%

mentions of soccer teams and players

No Comments

No Known Activations