INDEX

Explanations

technical jargon and terms related to education and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 latter

-0.23

ture

-0.16

eko

-0.14

xDF

-0.14

ho

-0.14

ello

-0.14

Dash

-0.14

thouse

-0.14

AIN

-0.14

Pragma

-0.14

POSITIVE LOGITS

/-

0.26

odore

0.25

atre

0.21

rÃ©

0.17

gether

0.17

adays

0.16

 arasÄ±

0.16

istant

0.16

-BEGIN

0.15

noon

0.15

Activations Density 0.369%

technical jargon and terms related to education and statistics

No Comments

No Known Activations