INDEX

Explanations

terms related to graphs and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 scal

-0.19

à¸²à¸ĩ

-0.16

 physical

-0.16

Pragma

-0.15

odelist

-0.15

ì²´

-0.15

 Physical

-0.14

umat

-0.14

 scalar

-0.14

loor

-0.14

POSITIVE LOGITS

prefix

0.17

iosa

0.17

 longest

0.17

 Stateless

0.17

FINITE

0.16

.minLength

0.16

 Productions

0.16

angu

0.16

 palindrome

0.16

-length

0.16

Activations Density 0.020%

terms related to graphs and their properties

No Comments

No Known Activations