INDEX

Explanations

phrases indicating certainty or lack of doubt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Ð¾Ð·

-0.14

basePath

-0.14

umer

-0.14

bourg

-0.14

Drv

-0.14

âĬ

-0.14

 sublic

-0.13

tÃ©

-0.13

ooth

-0.13

POSITIVE LOGITS

 doubt

0.40

 deny

0.33

 Doub

0.32

 denying

0.30

 dispute

0.30

 doubts

0.28

deny

0.27

 disput

0.26

 denies

0.25

 denial

0.25

Activations Density 0.046%

phrases indicating certainty or lack of doubt

No Comments

No Known Activations