INDEX

Explanations

key actions and roles related to professional or formal settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oyer

-0.15

 Woodward

-0.15

olar

-0.15

StackNavigator

-0.15

elor

-0.14

ãĥªãĥ³

-0.14

ä¸¸

-0.14

amient

-0.14

Entered

-0.14

ahat

-0.14

POSITIVE LOGITS

 Manson

0.15

Hen

0.15

otty

0.15

 KromÄĽ

0.15

ë£¡

0.14

_RS

0.14

bidden

0.14

ç£

0.14

iny

0.13

orde

0.13

Activations Density 0.016%

key actions and roles related to professional or formal settings

No Comments

No Known Activations