INDEX

Explanations

mathematical terminology and symbols related to 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ana

-0.16

-0.15

utherland

-0.15

utra

-0.15

rowser

-0.15

ecome

-0.14

Ð¾ÐºÐ¾Ð½

-0.14

hattan

-0.14

li

-0.14

isi

-0.14

POSITIVE LOGITS

celik

0.17

0.14

ÐµÐ½Ð¸

0.14

Ä±k

0.14

egers

0.14

.dsl

0.13

:disable

0.13

TEM

0.13

PLICIT

0.13

lÃ¡Å¡

0.12

Activations Density 0.011%

mathematical terminology and symbols related to functions and equations

No Comments

No Known Activations