INDEX

Explanations

specific numerical values or operations within mathematical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

________

-0.20

 ______

-0.17

âĢĮâĢĮ

-0.17

 "(\<

-0.15

 Ø¨Ø±Ø§ÙĬ

-0.15

ovaly

-0.14

!(:

-0.14

 ----------↵

-0.14

____________

-0.14

 !↵↵

-0.14

POSITIVE LOGITS

Ã

0.35

!!

0.35

!!

0.34

,,

0.34

??

0.34

<<

0.34

>>

0.33

%%

0.32

%%

0.32

>>

0.32

Activations Density 0.034%

specific numerical values or operations within mathematical contexts

No Comments

No Known Activations