INDEX

Explanations

terms related to various categories, such as music genres, descriptions of products, and attributes of services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 latter

-0.36

/her

-0.20

âĢĲ

-0.18

ses

-0.18

EGIN

-0.18

agua

-0.16

UGIN

-0.16

áº·p

-0.15

deaux

-0.15

-sided

-0.15

POSITIVE LOGITS

/-

0.48

gether

0.26

odore

0.25

atre

0.22

adays

0.22

ern

0.21

ir

0.20

-turned

0.20

edly

0.20

ÂĿ

0.19

Activations Density 0.800%

terms related to various categories, such as music genres, descriptions of products, and attributes of services

No Comments

No Known Activations