INDEX

Explanations

business-related terms and company identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

.ua

-0.16

asurer

-0.15

ardon

-0.15

ycin

-0.15

merican

-0.14

.lib

-0.14

ABCDEFGHIJKLMNOP

-0.14

phin

-0.14

anter

-0.13

isu

-0.13

POSITIVE LOGITS

 Limited

0.42

 limited

0.38

Pvt

0.38

 LIMITED

0.36

Limited

0.35

limited

0.34

Ltd

0.33

ltd

0.31

Pty

0.31

æľīéĻĲåħ¬åı¸

0.29

Activations Density 0.131%

business-related terms and company identifiers

No Comments

No Known Activations