INDEX

Explanations

programming and code-related keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

abe

-0.16

ÑıÐ¶

-0.15

aÃ§

-0.15

iazza

-0.14

greg

-0.14

ukt

-0.14

.scrollHeight

-0.14

usters

-0.14

Rai

-0.14

 Junction

-0.13

POSITIVE LOGITS

ooth

0.17

á»Ļng

0.15

edList

0.15

ya

0.14

ectors

0.14

hap

0.14

hart

0.14

åģı

0.14

 (;;)

0.14

ãģªãģĮ

0.13

Activations Density 0.065%

programming and code-related keywords

No Comments

No Known Activations