INDEX

Explanations

instances of the keyword "new" related to object creation 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 @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ramid

-0.16

vod

-0.15

.IContainer

-0.15

ckt

-0.14

volt

-0.14

cctor

-0.14

pii

-0.14

onse

-0.14

orro

-0.14

plex

-0.14

POSITIVE LOGITS

lun

0.20

_algo

0.15

loop

0.15

´Ģ

0.14

ivan

0.14

 BASIC

0.14

issa

0.14

slt

0.14

maal

0.13

gim

0.13

Activations Density 0.017%

instances of the keyword "new" related to object creation in programming

No Comments

No Known Activations