INDEX

Explanations

references to leadership and unity within a community or organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Levine

-0.17

 fucked

-0.17

-0.15

Å¾iv

-0.14

 Biblical

-0.14

shit

-0.14

 shit

-0.14

 fucking

-0.14

Sir

-0.14

 Rahman

-0.14

POSITIVE LOGITS

BYU

0.36

 Latter

0.34

LDS

0.31

 Mormon

0.30

 Utah

0.30

 Brigham

0.28

lds

0.27

 Elder

0.27

Doctrine

0.26

Nep

0.25

Activations Density 0.028%

references to leadership and unity within a community or organization

No Comments

No Known Activations