INDEX

Explanations

phrases related to charitable actions and support for vulnerable populations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Whites

-0.16

CHO

-0.16

lingen

-0.15

llib

-0.15

baugh

-0.15

EqualityComparer

-0.14

antan

-0.14

ãĥªãĤ«

-0.14

GLfloat

-0.14

entin

-0.14

POSITIVE LOGITS

 vulnerable

0.29

 Vulner

0.24

 vulner

0.22

 chron

0.22

 unders

0.20

 deserving

0.20

 abused

0.18

 lonely

0.18

 neglected

0.17

 disadv

0.17

Activations Density 0.220%

phrases related to charitable actions and support for vulnerable populations

No Comments

No Known Activations