INDEX

Explanations

intensifiers that emphasize emotions or states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 porad

-0.16

lotte

-0.15

anmar

-0.14

ëĿ¼ëıĦ

-0.14

unky

-0.14

ighth

-0.14

inator

-0.13

 Ø§ÙĦØ£ÙħØ±

-0.13

agraph

-0.13

aos

-0.13

POSITIVE LOGITS

 glad

0.22

oo

0.20

oper

0.20

OPER

0.18

OMPI

0.18

-o

0.17

ooo

0.17

so

0.17

-so

0.16

oooo

0.16

Activations Density 0.053%

intensifiers that emphasize emotions or states of being

No Comments

No Known Activations