INDEX

Explanations

quantifiable metrics and performance details related to racing experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

jam

-0.16

edly

-0.16

asics

-0.15

utzer

-0.15

ummer

-0.15

vang

-0.14

tel

-0.14

 Crime

-0.14

moon

-0.14

 prot

-0.13

POSITIVE LOGITS

 saya

0.21

my

0.17

 mijn

0.17

 myself

0.16

æĪĳçļĦ

0.16

 tÃ´i

0.16

estroy

0.16

iferay

0.15

 minha

0.15

/Branch

0.15

Activations Density 0.010%

quantifiable metrics and performance details related to racing experiences

No Comments

No Known Activations