INDEX

Explanations

mathematical notation and symbols related to equations

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

yst

-0.16

 Diet

-0.15

ating

-0.15

liÅ¡

-0.14

buch

-0.14

 Sanford

-0.14

subclass

-0.14

yes

-0.14

ipes

-0.14

 Inform

-0.14

POSITIVE LOGITS

0.17

Ã¡nÃŃ

0.16

eldo

0.15

Ã¡m

0.15

ptal

0.15

ensa

0.14

(animated

0.14

 amis

0.14

à¸ķà¸°

0.14

loub

0.14

Activations Density 0.074%

mathematical notation and symbols related to equations

No Comments

No Known Activations