INDEX

Explanations

references to programming functions and libraries related to data processing or I/O operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ulan

-0.15

ç«¹

-0.14

airro

-0.14

 ÑĥÐ³Ð¾Ð´

-0.13

angi

-0.13

 Hicks

-0.13

ham

-0.13

istrat

-0.13

 Comics

-0.13

 massa

-0.13

POSITIVE LOGITS

 video

0.26

 Video

0.24

motion

0.23

 vide

0.23

 motion

0.22

 Motion

0.22

video

0.21

Video

0.21

vide

0.20

 VIDEO

0.20

Activations Density 0.136%

references to programming functions and libraries related to data processing or I/O operations

No Comments

No Known Activations