INDEX

Explanations

references to sports championships and their associated teams or players

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IPA

-0.16

ÐµÑĢÐº

-0.15

 ç»ı

-0.15

æĢ

-0.15

 îł

-0.14

uchs

-0.14

ãģĺ

-0.14

echa

-0.14

ovky

-0.13

ollar

-0.13

POSITIVE LOGITS

 winning

0.30

 titles

0.30

won

0.28

 title

0.28

win

0.27

 winners

0.26

win

0.25

 winner

0.25

 trophy

0.25

-winning

0.24

Activations Density 0.267%

references to sports championships and their associated teams or players

No Comments

No Known Activations