INDEX

Explanations

a specific character or symbol that indicates a significant event or topic in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

éħįåĲĪ

-0.15

ç¥Ŀ

-0.14

Advice

-0.14

 advising

-0.14

 warnings

-0.13

 ÑģÐ¾Ð¿ÑĢÐ¾Ð²

-0.13

_icall

-0.12

 recommending

-0.12

Joined

-0.12

å®³

-0.12

POSITIVE LOGITS

 uncover

0.26

 exploration

0.24

 discovery

0.23

 elucid

0.22

 unravel

0.22

 explor

0.21

 discoveries

0.21

 unpack

0.21

 explore

0.21

 discover

0.20

Activations Density 0.131%

a specific character or symbol that indicates a significant event or topic in the text

No Comments

No Known Activations