INDEX

Explanations

references to experience and involvement in various industries, particularly in a business context

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

wang

-0.16

acher

-0.15

avr

-0.15

ĮĴ

-0.14

vala

-0.14

ead

-0.14

ACA

-0.14

è³

-0.13

ÐµÑĢÑĥ

-0.13

onn

-0.13

POSITIVE LOGITS

 Fortune

0.43

 fortune

0.36

 blue

0.30

 corpor

0.30

 mult

0.30

 large

0.29

Fort

0.27

FT

0.27

-mult

0.26

 Large

0.25

Activations Density 0.224%

references to experience and involvement in various industries, particularly in a business context

No Comments

No Known Activations