INDEX

Explanations

positive qualities and attributes related to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.16

 Ø²ÙĨ

-0.14

ÑĸÑģÐ½Ð¾

-0.14

-0.13

 Setting

-0.13

_resolution

-0.13

arning

-0.13

kos

-0.13

erty

-0.13

POSITIVE LOGITS

 presence

0.31

 personality

0.28

 Presence

0.25

 ability

0.24

presence

0.24

 sense

0.24

 manner

0.24

 demeanor

0.23

 gift

0.21

 voice

0.21

Activations Density 0.209%

positive qualities and attributes related to individuals

No Comments

No Known Activations