INDEX

Explanations

expressions of emotional well-being and physical sensations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

awe

-0.19

 Atom

-0.16

 Rough

-0.15

 Mess

-0.15

 sincerity

-0.15

 rough

-0.15

 affected

-0.14

tim

-0.14

abit

-0.14

xac

-0.14

POSITIVE LOGITS

 alive

0.18

ulfilled

0.17

 alert

0.17

 hydrated

0.17

alive

0.17

èĬĻ

0.16

 rested

0.16

zano

0.15

 Ø³Ø¹

0.15

æºª

0.15

Activations Density 0.077%

expressions of emotional well-being and physical sensations

No Comments

No Known Activations