INDEX

Explanations

references to the "System" namespace in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

oÄŁ

-0.15

odic

-0.15

VG

-0.14

lush

-0.14

stad

-0.14

lus

-0.14

ë¡Ŀ

-0.14

acters

-0.13

 Divide

-0.13

itical

-0.13

POSITIVE LOGITS

fol

0.19

fol

0.15

PUR

0.15

 ç§ĭ

0.14

ouser

0.13

 Christie

0.13

alien

0.13

akk

0.13

errer

0.13

 à¸¡à¸«

0.13

Activations Density 0.002%

references to the "System" namespace in programming contexts

No Comments

No Known Activations