INDEX

Explanations

mentions of the term "Yahoo."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ç©´

-0.16

ubyte

-0.16

Ð¾Ð¿Ð°Ñģ

-0.15

uC

-0.15

.wordpress

-0.14

 ofType

-0.14

ÏĦÏĥ

-0.14

 Wenger

-0.14

usb

-0.14

 Nile

-0.14

POSITIVE LOGITS

 Yahoo

0.33

Yahoo

0.31

 Mayer

0.28

 yahoo

0.25

.yahoo

0.23

yahoo

0.23

 Finance

0.19

 Mail

0.19

 mail

0.19

 Messenger

0.18

Activations Density 0.007%

mentions of the term "Yahoo."

No Comments

No Known Activations