INDEX

Explanations

programming-related terms and structures, particularly those involving data structures and management in software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Town

-0.16

 ZÃ¡p

-0.15

Town

-0.14

 town

-0.14

.labelX

-0.14

.WriteByte

-0.13

ignal

-0.13

.scalablytyped

-0.13

 towns

-0.13

 removeFrom

-0.13

POSITIVE LOGITS

.get

0.21

.getC

0.19

 RuntimeObject

0.18

.getId

0.17

.getName

0.17

.is

0.17

.getInstance

0.16

.getCurrent

0.16

.getX

0.16

.getLogger

0.15

Activations Density 0.175%

programming-related terms and structures, particularly those involving data structures and management in software development

No Comments

No Known Activations