INDEX

Explanations

technical terms and components related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

NP

-0.15

ÄĽj

-0.14

insk

-0.14

oho

-0.14

ãĤ¯ãĥª

-0.14

iosk

-0.13

 Rider

-0.13

 semiclassical

-0.13

 Jacqu

-0.13

Sat

-0.13

POSITIVE LOGITS

 stream

0.41

 Stream

0.38

 streams

0.37

 Streams

0.36

stream

0.33

Stream

0.33

 STREAM

0.32

-stream

0.32

(stream

0.32

Streams

0.31

Activations Density 0.002%

technical terms and components related to programming and software development

No Comments

No Known Activations