INDEX

Explanations

references to notable individuals and their associations with specific products or professions

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

åĲĲ

-0.16

Mej

-0.15

boy

-0.14

å·

-0.14

aku

-0.14

bet

-0.14

boy

-0.14

ubbo

-0.14

POSITIVE LOGITS

cih

0.17

ëł¹

0.16

 ØµØ§ÙĦØŃ

0.15

 ÙħØªØ¹Ø¯Ø¯

0.15

emente

0.15

GetMethod

0.14

Ð´Ð°Ð¼

0.14

iar

0.14

 Ø¨Ø®

0.14

Activations Density 0.004%

references to notable individuals and their associations with specific products or professions

No Comments

No Known Activations