INDEX

Explanations

technical terms and concepts related to data structures and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

aso

-0.15

awy

-0.14

åĪĩ

-0.14

 hart

-0.14

ien

-0.14

asy

-0.14

ous

-0.14

tow

-0.14

 Kale

-0.14

ASSERT

-0.14

POSITIVE LOGITS

 itself

0.18

 selectedItem

0.16

ohan

0.15

TestFixture

0.15

GIN

0.14

actionDate

0.14

rette

0.14

 ÄĳÃ£i

0.14

isclosed

0.14

ÐºÑĥÑģ

0.14

Activations Density 0.105%

technical terms and concepts related to data structures and programming

No Comments

No Known Activations