INDEX

Explanations

numerals or digits within 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 @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

CHASE

-0.14

habi

-0.14

uite

-0.14

 queryInterface

-0.14

uesday

-0.14

ãĤ¸ãĤ¢

-0.14

Ð»ÑİÐ´

-0.14

ippy

-0.13

ucs

-0.13

usic

-0.13

POSITIVE LOGITS

ê

0.17

ahu

0.15

erner

0.15

tero

0.15

0.14

pm

0.13

ê°ģ

0.13

etration

0.13

Activations Density 0.242%

numerals or digits within the text

No Comments

No Known Activations