INDEX

Explanations

programming-related syntax and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 public

-0.16

 Carl

-0.15

 union

-0.14

 Benson

-0.14

ahn

-0.14

hammer

-0.14

achten

-0.14

World

-0.14

public

-0.14

ens

-0.14

POSITIVE LOGITS

 print

0.34

def

0.32

print

0.26

	print

0.25

def

0.23

def

0.22

/print

0.20

-def

0.19

Def

0.19

 dÃ©f

0.19

Activations Density 0.040%

programming-related syntax and structure

No Comments

No Known Activations