INDEX

Explanations

numerical data and statistics related to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Bars

-0.17

ocoder

-0.15

 Brass

-0.14

-pres

-0.14

utenberg

-0.14

tty

-0.13

ãĥ¼ãĥĳãĥ¼

-0.13

ynn

-0.13

uxt

-0.13

 Roth

-0.13

POSITIVE LOGITS

 respectively

1.02

 respective

0.69

 ÑģÐ¾Ð¾ÑĤÐ²ÐµÑĤ

0.57

respect

0.50

åĪĨåĪ«

0.43

 Ð²ÑĸÐ´Ð¿Ð¾Ð²ÑĸÐ´Ð½Ð¾

0.36

 resp

0.34

ãģĿãĤĮ

0.34

,res

0.30

resp

0.29

Activations Density 0.086%

numerical data and statistics related to various topics

No Comments

No Known Activations