INDEX

Explanations

references to procedural or structural components within documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 such

-0.29

 Such

-0.26

such

-0.26

Such

-0.25

 SUCH

-0.24

è¿Ļæł·çļĦ

-0.23

 suche

-0.19

 takovÃ©

-0.19

 ello

-0.19

 these

-0.18

POSITIVE LOGITS

æľ¬

0.41

 THIS

0.40

 æľ¬

0.38

.this

0.37

 this

0.36

 ìĿ´ë²Ī

0.35

this

0.34

 ë³¸

0.34

$this

0.33

THIS

0.32

Activations Density 0.177%

references to procedural or structural components within documents

No Comments

No Known Activations