INDEX

Explanations

references to research articles and studies related to various scientific fields

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

 PLATFORM

-0.16

ÏĦÏī

-0.16

ëª»

-0.15

WX

-0.14

urer

-0.14

Cov

-0.14

Ð¸Ð½Ð¸

-0.14

sted

-0.13

 Kidd

-0.13

 Brother

-0.13

POSITIVE LOGITS

0.18

 Journal

0.17

 journal

0.16

rir

0.15

 Magazine

0.15

Riv

0.15

ergisi

0.15

 magazine

0.15

arget

0.14

Activations Density 0.462%

references to research articles and studies related to various scientific fields

No Comments

No Known Activations