INDEX

Explanations

technical terms and programming-related syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

oleon

-0.14

illard

-0.13

 Loud

-0.13

ph

-0.12

Ã¡p

-0.12

etti

-0.12

VERRIDE

-0.12

ãĤ¦ãĤ¹

-0.12

.openg

-0.12

zÃ¡

-0.12

POSITIVE LOGITS

 Phase

0.30

 Type

0.29

 Stage

0.28

 Level

0.28

 Region

0.27

 Step

0.27

 Name

0.26

 Point

0.26

 Area

0.26

 Position

0.25

Activations Density 0.207%

technical terms and programming-related syntax

No Comments

No Known Activations