INDEX

Explanations

expressions of well-wishing and positivity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

.scalablytyped

-0.17

OUN

-0.14

.LENGTH

-0.14

íĹĮ

-0.14

 èĩ

-0.14

WISE

-0.13

iral

-0.13

å§Ķåĵ¡

-0.13

emand

-0.13

adf

-0.13

POSITIVE LOGITS

 Happy

0.31

 safe

0.29

Happy

0.27

 Merry

0.26

 Safe

0.26

 Blessed

0.24

safe

0.24

 HAPP

0.23

 SAFE

0.23

 happy

0.23

Activations Density 0.028%

expressions of well-wishing and positivity

No Comments

No Known Activations