INDEX

Explanations

references to notable individuals and their works, particularly in the context of art and music

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

¹

-0.18

ÐºÑĥÐ»Ñı

-0.16

ongyang

-0.15

ucken

-0.14

ucked

-0.14

ileÅŁ

-0.14

ternet

-0.14

venir

-0.14

ayment

-0.14

omens

-0.14

POSITIVE LOGITS

 kalan

0.14

 Cooke

0.14

 Burada

0.14

alth

0.14

 jmÃ©

0.13

EDIA

0.13

ernity

0.13

ToLower

0.13

lod

0.13

Activations Density 0.163%

references to notable individuals and their works, particularly in the context of art and music

No Comments

No Known Activations