INDEX

Explanations

phrases related to business and professional roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 totiÅ¾

-0.18

 therefore

-0.16

áº£o

-0.15

æĺ¯ä¸Ģ

-0.14

 pÅĻiÄįemÅ¾

-0.14

 understandably

-0.14

æĺ¯ä¸Ģä¸ª

-0.14

 donc

-0.14

 indeed

-0.14

 )↵↵↵↵↵↵↵↵

-0.13

POSITIVE LOGITS

 otherwise

0.23

otherwise

0.18

 OTHERWISE

0.17

Otherwise

0.17

 Otherwise

0.16

 jinak

0.16

 later

0.15

 sonst

0.15

ched

0.14

-Ð»Ð¸Ð±Ð¾

0.14

Activations Density 0.546%

phrases related to business and professional roles

No Comments

No Known Activations