INDEX

Explanations

conditional statements and checks related to programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

lider

-0.15

warts

-0.15

rades

-0.15

iais

-0.14

 Julius

-0.14

SOR

-0.14

itters

-0.13

 quali

-0.13

 codes

-0.13

å·Ŀ

-0.13

POSITIVE LOGITS

 zbyt

0.18

andler

0.16

too

0.16

aris

0.14

chester

0.14

too

0.14

isNaN

0.14

TOO

0.14

 lacks

0.14

 EITHER

0.14

Activations Density 0.059%

conditional statements and checks related to programming

No Comments

No Known Activations