INDEX

Explanations

phrases that express a change in circumstances or states

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

 Junk

-0.18

endor

-0.17

Ð¾Ð»ÐµÑĤ

-0.15

WND

-0.14

ront

-0.14

Ã¼gen

-0.14

ufs

-0.14

elim

-0.14

inces

-0.14

 Ã©c

-0.13

POSITIVE LOGITS

-caption

0.19

#@

0.14

ignet

0.14

instein

0.14

VE

0.14

decorate

0.14

erto

0.14

anus

0.14

 settled

0.13

Activations Density 0.200%

phrases that express a change in circumstances or states

No Comments

No Known Activations