INDEX

Explanations

references to Greek terminology and their meanings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

omon

-0.15

esi

-0.15

ider

-0.14

iesz

-0.14

ello

-0.14

alette

-0.14

eso

-0.13

ucht

-0.13

illery

-0.13

ernels

-0.13

POSITIVE LOGITS

uar

0.16

istrovstvÃŃ

0.16

.tif

0.15

kt

0.15

ÙĪØ³ÛĮ

0.14

Ð¿Ðµ

0.14

Ã¡lido

0.14

oyer

0.13

é¢ĳæ¬¡

0.13

 èĢ

0.13

Activations Density 0.028%

references to Greek terminology and their meanings

No Comments

No Known Activations