INDEX

Explanations

mathematical terminology and definitions related to sets, functions, and mappings

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

anean

-0.16

deriv

-0.16

limits

-0.16

Spl

-0.15

 derivatives

-0.15

spl

-0.15

 Equal

-0.15

Ø¯ÛĮØ¯

-0.15

 Affero

-0.14

 gradients

-0.14

POSITIVE LOGITS

 family

0.32

 collection

0.30

 sequence

0.26

map

0.24

 function

0.24

 tuple

0.24

set

0.23

 subset

0.23

 system

0.22

family

0.22

Activations Density 0.128%

mathematical terminology and definitions related to sets, functions, and mappings

No Comments

No Known Activations