INDEX

Explanations

elements related to table structures and styling in code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

affe

-0.16

evice

-0.15

dn

-0.15

tea

-0.14

lox

-0.14

iesz

-0.14

 Families

-0.14

enant

-0.14

Tea

-0.14

wor

-0.14

POSITIVE LOGITS

Sharper

0.16

anny

0.15

ures

0.15

.smtp

0.15

è¸

0.15

 å¹

0.15

-Fi

0.14

anner

0.14

osten

0.14

rael

0.14

Activations Density 0.114%

elements related to table structures and styling in code

No Comments

No Known Activations