INDEX

Explanations

symbols or characters indicating importance or emphasis in digital communication

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

GMEM

-0.16

 getApp

-0.16

Ð¿ÑĢÐ¸ÐºÐ»Ð°Ð´

-0.15

 MyApp

-0.15

ãĥŃãĥ¼

-0.15

apol

-0.15

Buf

-0.15

ÑıÐ²Ð¸

-0.15

ÏĨÎ±Ïģ

-0.14

 Spinner

-0.14

POSITIVE LOGITS

Age

0.21

age

0.21

 ages

0.18

Age

0.17

pay

0.17

 Ages

0.17

_age

0.16

AGE

0.16

 aging

0.16

AGED

0.16

Activations Density 0.013%

symbols or characters indicating importance or emphasis in digital communication

No Comments

No Known Activations