INDEX

Explanations

references to various types of assays or diagnostic tests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 saja

-0.16

SingleOrDefault

-0.16

oren

-0.16

eller

-0.15

ì²Ļ

-0.15

 Included

-0.14

imo

-0.14

istrovstvÃŃ

-0.14

ellen

-0.14

POSITIVE LOGITS

 another

0.25

 equally

0.24

another

0.24

 similarly

0.21

 ná»¯a

0.21

 ebenfalls

0.20

 zase

0.19

ãģĵãģ¡ãĤī

0.19

åĲĮãģĺ

0.18

 smaller

0.18

Activations Density 0.162%

references to various types of assays or diagnostic tests

No Comments

No Known Activations