INDEX

Explanations

references to themes in collections or series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

oser

-0.19

-pill

-0.15

 Atlas

-0.15

 è¡ĮæĶ¿

-0.15

 atlas

-0.14

Atlas

-0.14

-setup

-0.14

 Majesty

-0.14

æļĸ

-0.14

POSITIVE LOGITS

icont

0.17

gaard

0.16

ington

0.15

ctp

0.15

endoza

0.15

Tenant

0.15

 Fletcher

0.14

ockets

0.14

.GraphicsUnit

0.14

phere

0.14

Activations Density 0.029%

references to themes in collections or series

No Comments

No Known Activations