INDEX

Explanations

references to specific data structures and variables in a programming or data context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

vale

-0.15

jours

-0.15

utas

-0.14

allis

-0.14

affer

-0.13

âĢı

-0.13

()

-0.13

/trunk

-0.13

 outsourcing

-0.13

ym

-0.13

POSITIVE LOGITS

 Plus

0.20

II

0.20

##_

0.20

 plus

0.18

 again

0.18

alt

0.18

 Lite

0.17

ëĵĿ

0.17

again

0.17

ä»¥å¤ĸ

0.16

Activations Density 0.370%

references to specific data structures and variables in a programming or data context

No Comments

No Known Activations