INDEX

Explanations

references to racing teams, events, and achievements in motorsports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

eon

-0.17

avors

-0.15

yb

-0.15

aight

-0.15

etak

-0.15

 demi

-0.14

AMED

-0.14

.Produ

-0.14

isphere

-0.14

 Ø§ÙĦÙħØ³

-0.14

POSITIVE LOGITS

 team

0.33

 Team

0.32

Team

0.28

team

0.27

 TEAM

0.24

 ÙģØ±ÙĬÙĤ

0.23

 equipe

0.22

.team

0.22

_team

0.22

-team

0.22

Activations Density 0.063%

references to racing teams, events, and achievements in motorsports

No Comments

No Known Activations