INDEX

Explanations

expressions of uncertainty or 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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ibus

-0.16

asters

-0.16

ibaba

-0.15

ertz

-0.15

mÃ¡n

-0.15

bearing

-0.14

¬¬

-0.14

lected

-0.14

 MainAxisAlignment

-0.14

adel

-0.14

POSITIVE LOGITS

åİŁåĽł

0.37

 reasons

0.35

 reason

0.32

 Reasons

0.29

reason

0.26

 ìĿ´ìľł

0.26

çĲĨçĶ±

0.26

Reason

0.25

 Ð¿ÑĢÐ¸ÑĩÐ¸Ð½Ð°

0.24

why

0.24

Activations Density 0.265%

expressions of uncertainty or introspective thoughts

No Comments

No Known Activations