INDEX

Explanations

mathematical notations and symbols related to equations and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 addCriterion

-0.16

="../../../

-0.15

ìĨĮê°ľ

-0.14

 Lund

-0.14

ALAR

-0.14

éŃĤ

-0.14

 forth

-0.13

bern

-0.13

alaria

-0.13

edic

-0.13

POSITIVE LOGITS

0.17

enda

0.17

\n

0.15

storybook

0.15

ENC

0.15

atrix

0.15

UTE

0.15

=}

0.14

vard

0.14

locker

0.14

Activations Density 0.084%

mathematical notations and symbols related to equations and functions

No Comments

No Known Activations