INDEX

Explanations

expressions of gratitude and thanks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

à¸ķà¸Ļ

-0.14

then

-0.14

orro

-0.14

claimed

-0.13

assadors

-0.13

virt

-0.13

ÑĢÑıÐ´

-0.13

ensen

-0.13

icker

-0.13

 maybe

-0.13

POSITIVE LOGITS

 everyone

0.36

 everybody

0.31

everyone

0.28

 Everyone

0.23

Everyone

0.22

 whoever

0.20

 anyone

0.19

our

0.19

 those

0.18

à¸ªà¸³à¸«à¸£

0.17

Activations Density 0.065%

expressions of gratitude and thanks

No Comments

No Known Activations