INDEX

Explanations

references to programming parameters and file handling in code documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ugal

-0.16

ç½²

-0.15

rana

-0.15

ander

-0.15

meric

-0.14

ignum

-0.14

postcode

-0.14

iban

-0.14

ester

-0.14

ursal

-0.14

POSITIVE LOGITS

Î²ÎŃÏģ

0.15

ITTLE

0.14

 Prest

0.14

 copp

0.13

/UIKit

0.13

ÙĲÙħ

0.13

ê·ł

0.13

Activations Density 0.004%

references to programming parameters and file handling in code documentation

No Comments

No Known Activations