INDEX

Explanations

programming-related concepts and keywords, particularly those associated with classes and interfaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ultz

-0.15

omap

-0.15

inja

-0.15

atrib

-0.15

ManagerInterface

-0.15

utin

-0.15

perator

-0.15

slots

-0.15

Enumerator

-0.14

ă

-0.14

POSITIVE LOGITS

{@

0.18

Spi

0.18

 delegate

0.17

ipel

0.16

ÃŃÅĻ

0.15

 Throw

0.15

IllegalArgumentException

0.15

 delegation

0.15

 thrown

0.15

bean

0.15

Activations Density 0.015%

programming-related concepts and keywords, particularly those associated with classes and interfaces

No Comments

No Known Activations