INDEX

Explanations

references to programming constructs and code elements related to object-oriented design and dependency injection

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

mpr

-0.16

 Depths

-0.16

ilib

-0.15

ppe

-0.15

ushman

-0.15

thresh

-0.14

blk

-0.14

Sig

-0.14

_mgr

-0.14

æ¯Ľ

-0.14

POSITIVE LOGITS

 domain

0.34

 Domain

0.33

Domain

0.30

domain

0.29

 DOMAIN

0.28

-domain

0.27

/domain

0.26

 Aggregate

0.25

(domain

0.25

Projection

0.25

Activations Density 0.016%

references to programming constructs and code elements related to object-oriented design and dependency injection

No Comments

No Known Activations