INDEX

Explanations

technical identifiers or references related to web resources or code

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

ulis

-0.17

 íİ¸

-0.15

vn

-0.14

ÐºÐ¾Ð·

-0.14

ÑĥÑĤÑĮ

-0.14

enson

-0.14

uman

-0.14

dup

-0.14

 subtraction

-0.13

cis

-0.13

POSITIVE LOGITS

ataire

0.19

ãģŁãĤī

0.17

ETYPE

0.17

ClientRect

0.15

quivo

0.15

ERGE

0.15

[~,

0.15

 å¿

0.14

buc

0.14

alborg

0.14

Activations Density 0.028%

technical identifiers or references related to web resources or code

No Comments

No Known Activations