INDEX

Explanations

phrases that discuss exceptions to rules or common beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ãĥ¼ãĥ

-0.15

iven

-0.14

 Shank

-0.14

 Ø±Ùħ

-0.14

ais

-0.14

AINS

-0.14

á»Ń

-0.14

Ã¡s

-0.14

maya

-0.14

unlikely

-0.13

POSITIVE LOGITS

 necessarily

0.62

ecessarily

0.40

 always

0.29

 Ð¾Ð±ÑıÐ·Ð°ÑĤÐµÐ»ÑĮÐ½Ð¾

0.28

 automatically

0.28

ä¸Ģå®ļ

0.27

å¿ħ

0.27

always

0.24

Always

0.24

 Always

0.24

Activations Density 0.185%

phrases that discuss exceptions to rules or common beliefs

No Comments

No Known Activations