INDEX

Explanations

numerical values related to specific events or statistics

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

igne

-0.14

leen

-0.14

owell

-0.13

oga

-0.13

oogle

-0.13

.CompareTag

-0.13

ulo

-0.13

overn

-0.13

atsby

-0.13

POSITIVE LOGITS

å¹´

0.28

æ¬§

0.23

-present

0.23

ëħĦëıĦ

0.21

 marks

0.21

 ëħĦ

0.21

 marked

0.21

ëħĦ

0.20

 å¹´

0.20

 yÄ±lÄ±

0.20

Activations Density 0.100%

numerical values related to specific events or statistics

No Comments

No Known Activations