INDEX

Explanations

references to technology products and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Gui

-0.18

ecl

-0.16

_NC

-0.15

aggio

-0.15

portlet

-0.14

BuilderInterface

-0.14

idity

-0.14

fed

-0.14

 Pruitt

-0.14

Gui

-0.13

POSITIVE LOGITS

 Snapdragon

0.28

Snap

0.27

Qual

0.27

 Qualcomm

0.24

So

0.23

oct

0.23

 snap

0.22

 chip

0.22

 chipset

0.22

 Snap

0.22

Activations Density 0.018%

references to technology products and specifications

No Comments

No Known Activations