INDEX

Explanations

mathematical symbols and notation indicating properties of functions and equations

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

inn

-0.15

enth

-0.14

ault

-0.14

enthal

-0.13

íĻĺê²½

-0.13

 puberty

-0.13

ç«ĭãģ¡

-0.13

ailles

-0.13

inis

-0.13

indexes

-0.13

POSITIVE LOGITS

 partic

0.15

rei

0.14

mlink

0.14

askan

0.14

arking

0.13

 Industry

0.13

.scala

0.13

ÐŁÐļ

0.13

ÑģÑĤÐ°

0.13

ployment

0.13

Activations Density 0.183%

mathematical symbols and notation indicating properties of functions and equations

No Comments

No Known Activations