INDEX

Explanations

terms associated with payroll and compensation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

bak

-0.15

antee

-0.15

wald

-0.14

eker

-0.13

aille

-0.13

poon

-0.13

zet

-0.13

Î»Î¹Î¿

-0.13

etal

-0.13

Kok

-0.13

POSITIVE LOGITS

ndef

0.15

tees

0.15

tery

0.15

arrants

0.14

adiens

0.14

.simps

0.14

ãĥ³ãĥĳ

0.14

Å¡Å¡ÃŃ

0.14

ondon

0.14

enburg

0.14

Activations Density 0.001%

terms associated with payroll and compensation

No Comments

No Known Activations