INDEX

Explanations

detailed cooking instructions and methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ischen

-0.18

lom

-0.15

 arguably

-0.15

ische

-0.14

unc

-0.14

-0.13

Ã´n

-0.13

Î¼Î·

-0.13

azu

-0.13

 located

-0.13

POSITIVE LOGITS

 Pressure

0.18

 Else

0.17

 pressure

0.16

pressure

0.16

Pressure

0.16

dal

0.16

Sie

0.16

 Mention

0.15

fen

0.15

mas

0.15

Activations Density 0.023%

detailed cooking instructions and methods

No Comments

No Known Activations