INDEX

Explanations

references to assistance and support offered by a company or service

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

hiba

-0.16

/cop

-0.15

axon

-0.15

ä¸įå¾Ĺ

-0.15

ãĥ

-0.15

estroy

-0.15

eld

-0.14

Î±ÏģÎ¬

-0.14

ÑĦÐµÑĢÐµÐ½

-0.14

å§«

-0.14

POSITIVE LOGITS

got

0.31

Got

0.30

Got

0.27

got

0.25

GOT

0.22

 here

0.18

onya

0.17

 ready

0.16

here

0.15

Cover

0.15

Activations Density 0.097%

references to assistance and support offered by a company or service

No Comments

No Known Activations