INDEX

Explanations

occurrence of the "@" symbol, often used in programming or markup syntax for annotations or directives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

LLU

-0.15

Fcn

-0.15

esteem

-0.15

/***/

-0.15

Ã¨m

-0.14

publication

-0.14

]("

-0.14

á»ĳi

-0.14

 massaggi

-0.14

CTL

-0.14

POSITIVE LOGITS

var

0.22

var

0.19

æļ

0.16

throws

0.16

return

0.15

ps

0.15

param

0.15

ICS

0.15

gar

0.15

 Brun

0.15

Activations Density 0.002%

occurrence of the "@" symbol, often used in programming or markup syntax for annotations or directives

No Comments

No Known Activations