INDEX

Explanations

references to various types of businesses and their classifications

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

ene

-0.18

URA

-0.16

 Claud

-0.15

deaux

-0.14

enes

-0.14

NonQuery

-0.14

jar

-0.14

yun

-0.14

is

-0.14

ugh

-0.14

POSITIVE LOGITS

rax

0.17

kdir

0.17

ertools

0.16

bris

0.16

BaseContext

0.16

resar

0.15

 magna

0.15

inesis

0.15

eydi

0.14

Ã¼lt

0.14

Activations Density 0.169%

references to various types of businesses and their classifications

No Comments

No Known Activations