INDEX

Explanations

phrases related to network building and design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

dbl

-0.16

deen

-0.15

orts

-0.15

strup

-0.15

onga

-0.15

.MixedReality

-0.15

Éµ

-0.14

è¾¦

-0.14

-toggler

-0.14

.CopyTo

-0.14

POSITIVE LOGITS

 appropriate

0.29

 suitable

0.25

appropriate

0.23

 equipment

0.22

 appropri

0.20

 layout

0.20

 hardware

0.19

 proper

0.19

 Equipment

0.19

 optimal

0.19

Activations Density 0.052%

phrases related to network building and design

No Comments

No Known Activations