INDEX

Explanations

statistical data and percentages related to research or studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

AIT

-0.16

ä½ĵ

-0.15

Ð¾Ñĥ

-0.15

AVE

-0.14

ven

-0.14

 Millions

-0.14

ibi

-0.13

loh

-0.13

sab

-0.13

Miy

-0.13

POSITIVE LOGITS

elight

0.16

ç§Ģ

0.16

essler

0.14

 creampie

0.14

ece

0.14

orget

0.14

uger

0.13

APS

0.13

 pupper

0.13

Activations Density 0.002%

statistical data and percentages related to research or studies

No Comments

No Known Activations