INDEX

Explanations

terms related to employer-employee relationships and employment agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

addock

-0.16

enheim

-0.16

Means

-0.15

 Ð½Ð°ÑĩÐ¸Ð½Ð°

-0.14

ibel

-0.14

 badge

-0.14

ÙĨØ²

-0.14

cus

-0.14

 unregister

-0.14

POSITIVE LOGITS

 signs

0.33

 forwards

0.32

 issues

0.31

 posts

0.30

ac

0.30

 Signs

0.28

 hands

0.28

issues

0.27

 files

0.27

 FILES

0.24

Activations Density 0.282%

terms related to employer-employee relationships and employment agreements

No Comments

No Known Activations