INDEX

Explanations

instances of enhancement or addition to elements in various contexts

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

 ìŀĳ

-0.16

oug

-0.16

ãģ»ãģ©

-0.14

æķı

-0.14

rew

-0.14

 clear

-0.14

aub

-0.14

avana

-0.14

-www

-0.14

ãĤ¼

-0.14

POSITIVE LOGITS

 dimension

0.23

 added

0.21

adds

0.21

 spice

0.20

 adds

0.19

 thÃªm

0.19

 Added

0.19

 Adds

0.18

 element

0.17

 Dimension

0.17

Activations Density 0.094%

instances of enhancement or addition to elements in various contexts

No Comments

No Known Activations

instances of enhancement or addition to elements in various contexts

No Comments

No Known Activations