INDEX

Explanations

references to awards and recognitions in the context of film and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

rint

-0.17

ÑıÐ·

-0.16

icum

-0.16

antz

-0.16

ounder

-0.15

olic

-0.15

opp

-0.14

ager

-0.14

zell

-0.14

abus

-0.14

POSITIVE LOGITS

 awards

0.49

 Awards

0.46

 award

0.41

 Award

0.39

 nominations

0.34

 nominees

0.32

award

0.32

Award

0.32

 awarded

0.30

 nomination

0.28

Activations Density 0.189%

references to awards and recognitions in the context of film and media

No Comments

No Known Activations