INDEX

Explanations

references to cities and geographic locations, particularly in relation to cultural and culinary experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 vista

-0.14

ì»¤

-0.14

Consum

-0.14

 diagnose

-0.13

XY

-0.13

 Ð¸ÑģÑħÐ¾Ð´

-0.13

apon

-0.13

consum

-0.13

ê¼

-0.13

 anticip

-0.13

POSITIVE LOGITS

 UNESCO

0.17

Ã±ana

0.15

 Best

0.15

 Shard

0.15

igram

0.15

olik

0.14

 Crate

0.14

 Defensive

0.14

 edible

0.13

 awakeFromNib

0.13

Activations Density 0.131%

references to cities and geographic locations, particularly in relation to cultural and culinary experiences

No Comments

No Known Activations