INDEX

Explanations

references to social status and personal insecurities related to one's appearance and circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

andra

-0.16

Ļ¨

-0.16

anager

-0.15

StackNavigator

-0.15

amik

-0.15

icha

-0.14

Ð¸Ð¼Ð²

-0.14

 Conce

-0.14

 èĲ

-0.13

tober

-0.13

POSITIVE LOGITS

 alongside

0.91

 beside

0.85

 next

0.77

next

0.65

 neben

0.61

 junto

0.57

 vedle

0.54

.next

0.52

-next

0.51

 Next

0.50

Activations Density 0.337%

references to social status and personal insecurities related to one's appearance and circumstances

No Comments

No Known Activations