INDEX

Explanations

assertions and questions regarding technology and service applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

adaki

-0.15

éĴ®

-0.14

 Carp

-0.14

 ÑģÐ¸

-0.14

ACHINE

-0.13

_kel

-0.13

ynamo

-0.13

afi

-0.13

etwork

-0.13

arna

-0.13

POSITIVE LOGITS

Toolkit

0.14

OUCH

0.13

AJ

0.13

abbo

0.13

lettes

0.13

ABC

0.13

orate

0.13

uzz

0.13

 tedy

0.13

Activations Density 0.161%

assertions and questions regarding technology and service applications

No Comments

No Known Activations