INDEX

Explanations

brands and product features related to technology and consumer goods

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

 sÃ¡t

-0.16

IFE

-0.14

fails

-0.14

quals

-0.14

ankind

-0.14

.ToShort

-0.14

	throws

-0.14

oulder

-0.13

 Kills

-0.13

 Saves

-0.13

POSITIVE LOGITS

has

0.36

is

0.35

isn

0.22

 does

0.22

 heeft

0.21

ãģ¯

0.20

 actually

0.20

 contains

0.20

can

0.20

 hasn

0.20

Activations Density 1.823%

brands and product features related to technology and consumer goods

No Comments

No Known Activations