INDEX

Explanations

specific technical terms or jargon used in software or digital content management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ips

-0.14

¶Į

-0.14

 bananas

-0.14

babel

-0.14

/WebAPI

-0.14

ABI

-0.14

 Copp

-0.13

 roma

-0.13

oha

-0.13

sip

-0.13

POSITIVE LOGITS

 Disk

0.29

Disk

0.26

 recovery

0.26

 disk

0.26

 scan

0.24

 Recover

0.24

 Recovery

0.24

 recover

0.24

 Partition

0.23

 recovering

0.23

Activations Density 0.015%

specific technical terms or jargon used in software or digital content management

No Comments

No Known Activations