INDEX

Explanations

numerical data related to business performance

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

lej

-0.17

kovi

-0.15

 substances

-0.15

enge

-0.14

iani

-0.14

 ÎłÎ»Î·

-0.14

 substance

-0.13

ì¦

-0.13

ngine

-0.13

 gren

-0.13

POSITIVE LOGITS

 franchise

0.39

 franch

0.35

 chain

0.34

 stores

0.31

 store

0.30

 franchises

0.29

 chains

0.29

 locations

0.29

 concept

0.28

chain

0.26

Activations Density 0.144%

numerical data related to business performance

No Comments

No Known Activations