INDEX

Explanations

phrases related to complex emotions and introspective thoughts

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

essler

-0.16

omi

-0.16

eldon

-0.14

aeda

-0.14

ling

-0.14

halb

-0.13

OTHER

-0.13

 khá»ıi

-0.13

POSITIVE LOGITS

 proceedings

0.28

 everything

0.25

ä¸ĢåĪĩ

0.24

everything

0.23

 tudo

0.22

 ello

0.20

 Everything

0.20

 things

0.20

 alles

0.19

Everything

0.18

Activations Density 0.528%

phrases related to complex emotions and introspective thoughts

No Comments

No Known Activations