INDEX

Explanations

mentions of "portfolio" and related terms indicating a collection or grouping of items or investments

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

alled

-0.15

jiang

-0.14

-0.13

berry

-0.13

iform

-0.13

ë¨¸ëĭĪ

-0.13

uhl

-0.13

tons

-0.13

/Dk

-0.13

POSITIVE LOGITS

 vitae

0.27

-wide

0.23

 size

0.23

 items

0.22

 sizes

0.21

-building

0.21

 members

0.20

 expansion

0.20

 list

0.20

items

0.19

Activations Density 0.105%

mentions of "portfolio" and related terms indicating a collection or grouping of items or investments

No Comments

No Known Activations