INDEX

Explanations

references to measurement or numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 vielen

-0.16

OrNil

-0.15

../../../../

-0.14

 Ð¼Ð½Ð¾Ð³Ð¸Ñħ

-0.14

 Several

-0.14

æīĢæľī

-0.14

ox

-0.14

 einzel

-0.14

 Ð±Ð°Ð³Ð°ÑĤÑĮÐ¾Ñħ

-0.14

è¯

-0.13

POSITIVE LOGITS

one

0.45

 first

0.38

åĪĨåĪ«

0.34

 ones

0.33

:first

0.32

 primero

0.32

first

0.31

 firstly

0.29

one

0.28

à¹ģà¸£à¸ģ

0.27

Activations Density 0.162%

references to measurement or numerical data

No Comments

No Known Activations