INDEX

Explanations

references to funding and grants for projects or initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ysz

-0.16

riter

-0.15

oulos

-0.15

ÅĻe

-0.15

adera

-0.15

eam

-0.14

osa

-0.14

Ĺi

-0.14

ulen

-0.14

argas

-0.14

POSITIVE LOGITS

mu

0.16

mal

0.15

mu

0.15

pe

0.15

FIELD

0.14

 Canter

0.13

å³

0.13

Mu

0.13

lic

0.13

ty

0.13

Activations Density 0.058%

references to funding and grants for projects or initiatives

No Comments

No Known Activations