INDEX

Explanations

mathematical notation and symbols used in formal definitions

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

Numeric

-0.15

Narr

-0.14

_CANNOT

-0.14

Buzz

-0.14

 Classified

-0.14

ieg

-0.13

anity

-0.13

ãĥ¼ãĥł

-0.13

Browsable

-0.13

á»ĳi

-0.12

POSITIVE LOGITS

 throughout

0.36

 Throughout

0.32

Throughout

0.31

 abusing

0.28

 abuse

0.27

 convention

0.25

 abused

0.25

den

0.25

den

0.24

 Abuse

0.24

Activations Density 0.166%

mathematical notation and symbols used in formal definitions

No Comments

No Known Activations