INDEX

Explanations

references to programming or software development concepts, particularly related to IntelliJ and its associated libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

.scalablytyped

-0.26

ovit

-0.16

loo

-0.16

rick

-0.15

loon

-0.15

Ð¸Ð»Ð¾

-0.14

loth

-0.14

ignon

-0.14

/cms

-0.14

ame

-0.14

POSITIVE LOGITS

.openapi

0.28

.psi

0.22

 IDEA

0.20

psi

0.20

.usage

0.20

IDE

0.19

.notification

0.18

.lang

0.18

ellij

0.18

.navigation

0.17

Activations Density 0.017%

references to programming or software development concepts, particularly related to IntelliJ and its associated libraries

No Comments

No Known Activations