INDEX

Explanations

references to anger and related emotional expressions

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

esser

-0.16

ä»¥ä¸Ĭ

-0.14

weeney

-0.14

erver

-0.14

elli

-0.14

elling

-0.14

 ÐŀÐ»ÐµÐºÑģÐ°Ð½Ð´

-0.14

UTO

-0.14

icari

-0.13

 interest

-0.13

POSITIVE LOGITS

ulent

0.16

íİ¸

0.15

æ´ŀ

0.15

orque

0.15

fulness

0.14

FUL

0.14

 Thur

0.14

unker

0.13

/conf

0.13

éĸĢ

0.13

Activations Density 0.040%

references to anger and related emotional expressions

No Comments

No Known Activations