INDEX

Explanations

mathematical references and citations in a formal document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ouse

-0.18

oga

-0.18

opp

-0.15

/power

-0.13

eenth

-0.13

 hawk

-0.13

olves

-0.13

AccessException

-0.13

OperationException

-0.13

-white

-0.13

POSITIVE LOGITS

rosso

0.16

instein

0.16

wner

0.15

unker

0.14

å¤©åłĤ

0.14

è£

0.14

0.13

á»ĭch

0.13

Ej

0.13

Activations Density 0.080%

mathematical references and citations in a formal document

No Comments

No Known Activations