INDEX

Explanations

nested mathematical expressions 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 @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

>NN

-0.18

bang

-0.16

prite

-0.15

imers

-0.14

woo

-0.14

allax

-0.14

asser

-0.14

agos

-0.14

pyx

-0.14

 ÑģÐºÐ»Ð°Ð´Ñĥ

-0.14

POSITIVE LOGITS

xit

0.14

ZY

0.14

ancell

0.14

NES

0.13

 solver

0.13

vard

0.13

Ã³m

0.13

orton

0.13

rella

0.13

Activations Density 0.023%

nested mathematical expressions and equations

No Comments

No Known Activations

nested mathematical expressions and equations

No Comments

No Known Activations