INDEX

Explanations

references to features and capabilities of technology or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

youtube

-0.18

.appspot

-0.16

ogle

-0.16

.wordpress

-0.16

xlsx

-0.16

wordpress

-0.15

.wik

-0.15

engo

-0.15

 wikipedia

-0.15

 youtube

-0.15

POSITIVE LOGITS

SG

0.29

hyp

0.23

WWW

0.23

Hyp

0.22

 Hyper

0.21

 Nets

0.21

 Lotus

0.20

 Electronic

0.20

 Internet

0.20

sg

0.20

Activations Density 0.041%

references to features and capabilities of technology or products

No Comments

No Known Activations