INDEX

Explanations

quoted speech or dialogue

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

-0.94

Ùĩ

-0.49

ska

-0.38

sburg

-0.38

-0.37

sar

-0.34

sand

-0.33

sik

-0.32

scape

-0.30

sian

-0.29

POSITIVE LOGITS

odore

0.28

atre

0.27

ÑįÑĤÐ¾Ð¼Ñĥ

0.26

etheless

0.22

adays

0.22

bsites

0.19

gether

0.19

alog

0.18

quarters

0.18

tlement

0.17

Activations Density 0.218%

quoted speech or dialogue

No Comments

No Known Activations