INDEX

Explanations

instances of jokes or humor in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

¯

-0.15

@Id

-0.14

ÑĥÑĩ

-0.14

nda

-0.14

unner

-0.14

 tract

-0.14

utz

-0.14

wahl

-0.14

enet

-0.13

Ð½Ð³

-0.13

POSITIVE LOGITS

sworth

0.16

sg

0.15

ä»ķ

0.15

mdi

0.14

.mount

0.14

odÃŃ

0.14

SG

0.14

turnstile

0.13

 seins

0.13

ingly

0.13

Activations Density 0.020%

instances of jokes or humor in the text

No Comments

No Known Activations