INDEX

Explanations

terms related to professionals and their roles or functions

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

Ð¿Ð¾Ð½

-0.16

ÐµÐ»Ñİ

-0.16

 ãģ¿

-0.16

 elders

-0.15

 newcomers

-0.14

 bosses

-0.14

 Visitors

-0.14

 newcomer

-0.14

rell

-0.14

 Incontri

-0.14

POSITIVE LOGITS

 drivers

0.47

 riders

0.43

 driver

0.43

 Drivers

0.39

drivers

0.38

 rider

0.38

 players

0.37

 athletes

0.36

driver

0.35

-driver

0.35

Activations Density 0.387%

terms related to professionals and their roles or functions

No Comments

No Known Activations