INDEX

Explanations

programming-related technical terms and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

oa

-0.15

_________________↵↵

-0.15

Ã¼ÄŁ

-0.14

readcr

-0.14

-validator

-0.14

elage

-0.14

 Uncategorized

-0.14

íĨµìĭł

-0.14

à¹ģà¸Ķà¸ĩ

-0.13

 eskort

-0.13

POSITIVE LOGITS

.getSystemService

0.16

esium

0.15

 foregoing

0.15

arkin

0.15

acket

0.13

orias

0.13

pes

0.13

nothrow

0.13

Activations Density 0.587%

programming-related technical terms and functions

No Comments

No Known Activations