INDEX

Explanations

technical terms and concepts related to data evaluation and machine learning frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Ķ

-0.18

dej

-0.17

ryn

-0.16

 Grinder

-0.14

uom

-0.14

TeX

-0.14

rug

-0.14

rnek

-0.14

ì§Ģê°Ģ

-0.13

 Mediterr

-0.13

POSITIVE LOGITS

 applied

0.16

ache

0.15

enburg

0.14

 algorithm

0.14

bject

0.14

ensus

0.14

 Correspond

0.13

reau

0.13

Ľå»º

0.13

alg

0.13

Activations Density 0.067%

technical terms and concepts related to data evaluation and machine learning frameworks

No Comments

No Known Activations