INDEX

Explanations

instances of gratitude or expressions of thanks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ynn

-0.18

Jad

-0.17

ÐµÐ»Ð¸Ðº

-0.16

ded

-0.16

addock

-0.15

 coat

-0.15

Ded

-0.15

Ã¤re

-0.15

_factory

-0.15

 DÃ¼n

-0.14

POSITIVE LOGITS

omik

0.15

Ð½ÑĥÐ»

0.15

ono

0.14

HEME

0.14

enha

0.14

iyim

0.14

Ø±ÙģØª

0.14

(;;

0.14

amo

0.14

ãĤ¹ãĤ¿ãĥ¼

0.13

Activations Density 0.037%

instances of gratitude or expressions of thanks

No Comments

No Known Activations