INDEX

Explanations

phrases related to scientific findings and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ss

-0.17

sss

-0.15

åı¸

-0.14

Media

-0.14

ÃĶ

-0.14

ember

-0.14

_MSB

-0.14

Ð¼Ð¾Ð½

-0.14

oke

-0.13

 Parad

-0.13

POSITIVE LOGITS

 alike

0.25

ahlen

0.16

aku

0.15

ÑĭÑĪ

0.15

Yii

0.15

 combo

0.14

(gcf

0.14

tul

0.14

 Ø¨ÛĮØ±

0.14

ActionResult

0.14

Activations Density 0.410%

phrases related to scientific findings and their implications

No Comments

No Known Activations