INDEX

Explanations

references to different departments and their roles or statuses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

sut

-0.18

sports

-0.17

iferay

-0.16

ubyte

-0.15

mer

-0.15

Ã¡bado

-0.14

ìļ´ëį°

-0.14

ingly

-0.14

ups

-0.14

utf

-0.14

POSITIVE LOGITS

al

0.22

alist

0.18

als

0.17

artment

0.17

sons

0.17

shire

0.16

ial

0.16

 Walsh

0.16

ally

0.16

nbsp

0.15

Activations Density 0.034%

references to different departments and their roles or statuses

No Comments

No Known Activations