INDEX

Explanations

constructs related to code structure and logic flow in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ones

-0.16

ensen

-0.15

tility

-0.14

erten

-0.14

 Hlav

-0.14

|required

-0.13

APER

-0.13

afen

-0.13

adu

-0.13

ï»¿using

-0.13

POSITIVE LOGITS

#else

0.36

 rather

0.36

}else

0.31

rather

0.29

 instead

0.28

 Rather

0.28

 otherwise

0.27

#elif

0.27

 whereas

0.27

 Otherwise

0.26

Activations Density 0.147%

constructs related to code structure and logic flow in programming

No Comments

No Known Activations