INDEX

Explanations

references to specific products and their market availability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Maul

-0.21

 Mayer

-0.20

 Moody

-0.19

 Mull

-0.19

 Mattis

-0.19

Mim

-0.18

Mapper

-0.17

_mapper

-0.17

 Mapper

-0.17

 Morse

-0.17

POSITIVE LOGITS

 market

0.78

market

0.63

 markets

0.62

 Market

0.61

å¸Ĥåľº

0.60

-market

0.60

 MARK

0.59

å¸Ĥåł´

0.56

_market

0.55

Market

0.54

Activations Density 0.208%

references to specific products and their market availability

No Comments

No Known Activations