INDEX

Explanations

expressions of gratitude and positive experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

wis

-0.15

WTF

-0.15

à¤¶à¤ķ

-0.14

iq

-0.14

 áº¥n

-0.14

 impress

-0.14

uko

-0.14

 Gest

-0.13

.names

-0.13

vys

-0.13

POSITIVE LOGITS

Fab

0.34

Fab

0.32

fab

0.31

Wonder

0.29

 great

0.28

 wonderful

0.26

 grand

0.25

 wonder

0.25

fab

0.24

 Wonderful

0.24

Activations Density 0.228%

expressions of gratitude and positive experiences

No Comments

No Known Activations