INDEX

Explanations

descriptions of ideal or perfect gifts and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

.scalablytyped

-0.14

isine

-0.13

PGA

-0.13

 ÙĪØ£ÙĨ

-0.13

 magg

-0.12

erosis

-0.12

_TYP

-0.12

ì§Ī

-0.12

éŁ¿

-0.12

 belli

-0.12

POSITIVE LOGITS

way

0.39

 addition

0.29

 treat

0.28

 excuse

0.27

 alternative

0.26

 diversion

0.26

 change

0.25

 complement

0.24

 option

0.24

 accom

0.24

Activations Density 0.122%

descriptions of ideal or perfect gifts and experiences

No Comments

No Known Activations