INDEX

Explanations

programming-related syntax and structure within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ern

-0.16

nu

-0.16

lich

-0.15

en

-0.15

ster

-0.14

ConnectionFactory

-0.14

chosen

-0.14

 grounds

-0.14

 loosen

-0.14

ani

-0.13

POSITIVE LOGITS

Specifier

0.18

 Catch

0.15

ì±Ħ

0.15

.wx

0.14

Bindable

0.14

ivals

0.14

.catch

0.14

vae

0.14

esium

0.14

-translate

0.14

Activations Density 0.008%

programming-related syntax and structure within code

No Comments

No Known Activations