INDEX

Explanations

product-related terms and categories, particularly in the context of health and personal care items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ä¹ĭä¸Ģ

-0.15

Ð¾Ð´ÐµÑĢÐ¶

-0.15

ledi

-0.14

.tw

-0.14

lements

-0.14

LAY

-0.13

 incre

-0.13

stra

-0.13

ponents

-0.13

.uml

-0.13

POSITIVE LOGITS

 list

0.23

 database

0.22

by

0.22

 directory

0.22

 alphabetical

0.22

 near

0.21

 finder

0.21

list

0.20

 index

0.20

Activations Density 0.249%

product-related terms and categories, particularly in the context of health and personal care items

No Comments

No Known Activations