INDEX

Explanations

terms related to scientific publications and research outputs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Ella

-0.16

inv

-0.15

çģ

-0.14

atar

-0.14

atsu

-0.14

dst

-0.14

-0.13

 Meng

-0.13

 liable

-0.13

POSITIVE LOGITS

 database

0.26

æķ°æį®åºĵ

0.23

 databases

0.22

database

0.21

.nlm

0.20

_database

0.20

 Database

0.20

_Abstract

0.19

abstract

0.18

Database

0.18

Activations Density 0.091%

terms related to scientific publications and research outputs

No Comments

No Known Activations