INDEX

Explanations

code syntax and structure related to programming and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

addtogroup

-0.20

}elseif

-0.18

peare

-0.16

BuilderInterface

-0.16

defgroup

-0.15

/apt

-0.15

println

-0.14

ColumnsMode

-0.14

	writel

-0.14

imoto

-0.14

POSITIVE LOGITS

 delete

0.39

delete

0.34

 deleted

0.31

 Object

0.30

.delete

0.29

 deletion

0.29

 Delete

0.28

 deleting

0.28

 Deleting

0.28

	delete

0.27

Activations Density 0.545%

code syntax and structure related to programming and function definitions

No Comments

No Known Activations