INDEX

Explanations

prominent names and titles associated with awards or recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

alse

-0.18

ptions

-0.17

 motor

-0.15

eb

-0.15

_embed

-0.15

Jun

-0.14

Shi

-0.14

MBED

-0.14

unsch

-0.14

 tast

-0.14

POSITIVE LOGITS

 ÑĥÑģ

0.15

ê°ľë¥¼

0.15

Æ°á»Łng

0.14

uges

0.14

æķ·

0.14

<System

0.14

Ð»Ð¸Ñħ

0.14

 sert

0.14

.getOwnProperty

0.14

áºŃu

0.13

Activations Density 0.100%

prominent names and titles associated with awards or recognitions

No Comments

No Known Activations