INDEX

Explanations

technical details and attributes related to coding practices

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

PTS

-0.16

awi

-0.16

egt

-0.15

agrid

-0.15

BoxLayout

-0.15

Æ°á»Łng

-0.14

PLEX

-0.14

 adel

-0.14

illez

-0.14

 UObject

-0.14

POSITIVE LOGITS

 hover

0.44

 mouse

0.42

 Mouse

0.39

hover

0.38

 Hover

0.37

 hovered

0.36

:hover

0.36

.hover

0.36

-hover

0.35

 onMouse

0.34

Activations Density 0.125%

technical details and attributes related to coding practices

No Comments

No Known Activations