INDEX

Explanations

technical terms and attributes related to programming and engineering concepts

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

ãģ°

-0.14

 Cors

-0.14

à¸Ńà¸¢

-0.14

loor

-0.14

 Ø§ÙĦØ¹Ùħ

-0.14

 Hindered

-0.13

kit

-0.13

 ÐºÐ°ÑĦÐµÐ´

-0.13

ÑģÐºÐ°

-0.13

à¹ģà¸Ł

-0.13

POSITIVE LOGITS

pto

0.16

uentes

0.15

dish

0.15

aits

0.15

usi

0.14

/Instruction

0.14

eph

0.14

 Lips

0.14

 rever

0.14

 TMPro

0.14

Activations Density 0.184%

technical terms and attributes related to programming and engineering concepts

No Comments

No Known Activations