INDEX

Explanations

cited salaries and compensation figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

orrow

-0.16

Ã¢m

-0.15

 Customers

-0.15

 venta

-0.15

borrow

-0.14

geme

-0.14

ÙĬÙĦØ§

-0.14

Purchase

-0.14

hlen

-0.13

 Inventory

-0.13

POSITIVE LOGITS

 salary

0.54

 salaries

0.53

 wages

0.50

pay

0.49

 wage

0.46

 Salary

0.44

salary

0.43

 compensation

0.42

Salary

0.40

Sal

0.38

Activations Density 0.292%

cited salaries and compensation figures

No Comments

No Known Activations