INDEX

Explanations

phrases related to themes and topics, particularly in celebrations and discussions

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

lesia

-0.15

amm

-0.14

istor

-0.14

IMATE

-0.14

ãģĸ

-0.13

ORIZ

-0.13

HWND

-0.13

è¼Ŀ

-0.13

anter

-0.13

_MIX

-0.13

POSITIVE LOGITS

 theme

0.89

 themes

0.77

 Theme

0.75

theme

0.73

Theme

0.68

-theme

0.65

 Themes

0.63

 THEME

0.63

_theme

0.59

themes

0.57

Activations Density 0.227%

phrases related to themes and topics, particularly in celebrations and discussions

No Comments

No Known Activations