INDEX

Explanations

references to technology and its functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

borough

-0.16

abet

-0.15

 Restoration

-0.15

 quake

-0.14

CAD

-0.14

 Telephone

-0.14

abi

-0.14

à¸²à¸ļ

-0.13

okit

-0.13

/Admin

-0.13

POSITIVE LOGITS

 RFID

0.37

RF

0.31

 reader

0.30

 readers

0.27

 tags

0.27

 Reader

0.26

NFC

0.25

RF

0.25

reader

0.25

tag

0.25

Activations Density 0.010%

references to technology and its functionalities

No Comments

No Known Activations