INDEX

Explanations

web-related terminology and event details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

/tutorial

-0.13

 Aluminium

-0.13

KeyType

-0.13

olem

-0.13

 Leakage

-0.13

SizePolicy

-0.13

ëĤĺëĿ¼

-0.13

incip

-0.13

é±

-0.13

 Ø´Ø±ØŃ

-0.13

POSITIVE LOGITS

 events

0.28

 Events

0.27

 calendar

0.27

 listings

0.27

 Listings

0.26

 EVENTS

0.26

 Calendar

0.25

 arts

0.25

 Local

0.25

 Dining

0.25

Activations Density 0.140%

web-related terminology and event details

No Comments

No Known Activations