INDEX

Explanations

technical terms related to networking standards and performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ustain

-0.16

 Hatch

-0.14

 Charl

-0.14

ton

-0.14

 Birch

-0.14

 Ther

-0.14

 Flam

-0.13

anford

-0.13

 Guns

-0.13

POSITIVE LOGITS

 Licensed

0.21

gig

0.20

 mesh

0.20

Licensed

0.19

mesh

0.19

 licensed

0.19

licensed

0.18

 cellular

0.18

 mill

0.18

Activations Density 0.078%

technical terms related to networking standards and performance metrics

No Comments

No Known Activations