INDEX

Explanations

high levels of emotional responses or expressions in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 ÑįÐºÑģÐ¿Ð»ÑĥÐ°ÑĤÐ°

-0.25

 Ð¾ÑĢÐ³Ð°Ð½Ð¸Ð·Ð°

-0.25

 Ð¸Ð½ÑĦÐ¾ÑĢÐ¼Ð°

-0.22

 Ð·Ð°ÑıÐ²

-0.21

 Ð¸Ð¼Ñĥ

-0.20

 Ð¿ÑĢÐ¾ÑĦÐµÑģÑģÐ¸Ð¾Ð½Ð°Ð»ÑĮ

-0.20

 ÐµÐ»ÐµÐºÑĤÑĢÐ¾Ð½

-0.19

 ÐµÐ»ÐµÐº

-0.19

 ÑįÑĦÑĦÐµÐº

-0.18

 ÑĦÐµÐ´ÐµÑĢÐ°Ð»ÑĮ

-0.18

POSITIVE LOGITS

 Ð¿Ð¾Ð±Ð°

0.17

itti

0.16

 Ð¾Ð±Ð¾

0.15

ä»Ģ

0.15

 Äįlov

0.14

µľ

0.14

ogl

0.14

beit

0.14

own

0.14

anza

0.14

Activations Density 0.018%

high levels of emotional responses or expressions in a text

No Comments

No Known Activations