INDEX

Explanations

references to personalization and uniqueness in contexts like photos, markets, designs, and client relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

okus

-0.17

ä¸ĢåĪĩ

-0.17

 Ð²Ð¾Ð¾Ð±ÑīÐµ

-0.16

swick

-0.16

 frequently

-0.16

Ã¤nge

-0.15

 vÅ¯bec

-0.15

kiye

-0.15

enga

-0.15

 ÙĥØ«ÙĬØ±

-0.15

POSITIVE LOGITS

 unique

0.32

 differently

0.30

unique

0.28

 respective

0.28

 different

0.28

 individually

0.27

 Unique

0.26

Unique

0.26

_unique

0.26

 respectively

0.26

Activations Density 0.328%

references to personalization and uniqueness in contexts like photos, markets, designs, and client relationships

No Comments

No Known Activations