INDEX

Explanations

specifications and measurements related to products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Warwick

-0.15

:CGRect

-0.15

inic

-0.14

BufferSize

-0.14

abei

-0.14

 YaÅŁ

-0.14

atik

-0.14

atica

-0.14

ukt

-0.13

Ãłn

-0.13

POSITIVE LOGITS

 depth

0.31

depth

0.29

 Depth

0.27

 depths

0.26

 volume

0.26

 volumes

0.25

-depth

0.25

Depth

0.25

 Volume

0.24

Volume

0.21

Activations Density 0.042%

specifications and measurements related to products

No Comments

No Known Activations