INDEX

Explanations

references to different fields or areas of focus related to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

upe

-0.18

esseract

-0.15

 empt

-0.14

.simps

-0.14

ryo

-0.14

 destin

-0.14

obi

-0.14

ew

-0.14

orque

-0.13

eru

-0.13

POSITIVE LOGITS

åŁŁ

0.16

 areas

0.16

areas

0.16

mmc

0.15

 Woodward

0.15

.cn

0.15

à¥Ģà¤¯

0.15

.ads

0.15

éº¦

0.15

exp

0.14

Activations Density 0.061%

references to different fields or areas of focus related to various topics

No Comments

No Known Activations