INDEX

Explanations

references to legal and business terminology related to organizations

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

/remove

-0.35

/disable

-0.27

ings

-0.27

ify

-0.26

/write

-0.26

/delete

-0.26

able

-0.24

/close

-0.22

/save

-0.22

ified

-0.22

POSITIVE LOGITS

redients

0.37

/loading

0.36

ly

0.36

redient

0.33

ton

0.32

/testing

0.31

/logging

0.30

enuity

0.28

tons

0.26

-edge

0.25

Activations Density 1.761%

references to legal and business terminology related to organizations

No Comments

No Known Activations