INDEX

Explanations

settings related to code formatting and indentation options

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

éĬ

-0.15

acha

-0.15

Ã©li

-0.14

-self

-0.14

xm

-0.14

 ÑģÐµÐ»

-0.14

Din

-0.14

Lad

-0.13

_charset

-0.13

POSITIVE LOGITS

berman

0.15

kaf

0.14

boa

0.14

 Ð¾ÑĤ

0.14

ÑĩÐ¸Ð½

0.13

Ð¾Ð»Ñı

0.13

à¸£à¸ĵ

0.13

 audiences

0.13

iling

0.13

ropa

0.13

Activations Density 0.015%

settings related to code formatting and indentation options

No Comments

No Known Activations