INDEX

Explanations

statements emphasizing lessons learned and important truths in various contexts

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

atan

-0.18

ulle

-0.17

atern

-0.15

antry

-0.15

uren

-0.15

ntax

-0.14

ipple

-0.14

à¸ªà¸ģ

-0.14

ires

-0.14

aje

-0.14

POSITIVE LOGITS

nik

0.16

tap

0.15

if

0.14

àµįà´

0.14

lej

0.14

 arts

0.14

 lÃłng

0.13

htub

0.13

 ÐļÐ¾Ð»Ð¸

0.13

OrDefault

0.13

Activations Density 0.277%

statements emphasizing lessons learned and important truths in various contexts

No Comments

No Known Activations