INDEX

Explanations

numerical data and coding elements related to values or parameters

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/pm

-0.15

pm

-0.15

dec

-0.15

Vel

-0.14

ä¹±

-0.14

ecs

-0.14

elper

-0.14

inker

-0.14

 offices

-0.14

POSITIVE LOGITS

Ð¼Ð¸Ð½Ð¸ÑģÑĤÑĢÐ°

0.17

amine

0.17

Zuk

0.17

illian

0.15

lÃ¡n

0.15

zem

0.15

 Stud

0.15

apy

0.14

ippo

0.14

roupe

0.14

Activations Density 0.038%

numerical data and coding elements related to values or parameters

No Comments

No Known Activations