INDEX

Explanations

phrases or sentences that express a sense of importance or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ugg

-0.16

imits

-0.16

ä¿Ĺ

-0.14

 ÙħØ±Ú©

-0.13

ippi

-0.13

Ã¼ven

-0.13

ivement

-0.13

ä¹ĭ

-0.13

 INTERFACE

-0.13

eniable

-0.12

POSITIVE LOGITS

 important

0.19

 something

0.18

gon

0.18

 interesting

0.17

 like

0.16

mium

0.15

uki

0.15

 very

0.15

fluid

0.15

nice

0.14

Activations Density 0.113%

phrases or sentences that express a sense of importance or significance

No Comments

No Known Activations