INDEX

Explanations

syntax elements and structure within programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

arma

-0.15

 public

-0.15

public

-0.15

ajas

-0.14

 PUBLIC

-0.14

reira

-0.14

idelity

-0.14

rvine

-0.14

æľ¬

-0.13

eree

-0.13

POSITIVE LOGITS

def

0.42

 print

0.39

print

0.32

 import

0.30

def

0.29

def

0.27

	print

0.27

-def

0.26

.def

0.23

/print

0.23

Activations Density 0.052%

syntax elements and structure within programming code

No Comments

No Known Activations