INDEX

Explanations

terms and phrases related to document reproduction and copyright

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

 Cooke

-0.16

æ¬¾

-0.16

 model

-0.15

 stick

-0.14

 uniform

-0.14

upy

-0.14

pty

-0.14

eday

-0.14

 State

-0.14

emplate

-0.14

POSITIVE LOGITS

ADVERTISEMENT

0.18

 kabil

0.17

ãĥ³ãĥģ

0.16

 Ø§ÙĦÙĤØ±

0.16

wing

0.15

ÏģÎº

0.15

Ð²Ð¾Ð·

0.14

Eng

0.14

iá»ĩt

0.14

engu

0.14

Activations Density 0.007%

terms and phrases related to document reproduction and copyright

No Comments

No Known Activations