INDEX

Explanations

content related to sharing and social media interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

rana

-0.17

idar

-0.16

ellers

-0.15

lop

-0.15

inder

-0.15

imu

-0.14

anner

-0.14

olerance

-0.14

upo

-0.14

á»¯

-0.14

POSITIVE LOGITS

 social

0.21

sharing

0.18

 sharing

0.18

social

0.18

 Social

0.17

 SOCIAL

0.17

/share

0.17

 spreading

0.16

 Share

0.16

share

0.16

Activations Density 0.031%

content related to sharing and social media interactions

No Comments

No Known Activations