INDEX

Explanations

phrases that indicate significant statements or important information

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

ãģĿ

-0.14

ansom

-0.14

ãģĦãĤĦ

-0.14

DAQ

-0.14

ÐµÐ¹ÑģÑĤÐ²

-0.14

imore

-0.14

 froze

-0.14

VERR

-0.13

ippo

-0.13

 ÑĢÐ°Ð·Ð²Ð¸

-0.13

POSITIVE LOGITS

 includes

0.24

 alone

0.21

 include

0.20

 applies

0.19

way

0.19

 means

0.18

 ranges

0.18

 ranged

0.18

can

0.17

alone

0.17

Activations Density 0.095%

phrases that indicate significant statements or important information

No Comments

No Known Activations