INDEX

Explanations

terms related to academic or professional roles and practices in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ØŃÙĦ

-0.13

Ìģc

-0.13

abc

-0.13

pany

-0.13

umper

-0.13

erce

-0.13

¥Ĳ

-0.13

 Sanat

-0.13

PIE

-0.13

plug

-0.13

POSITIVE LOGITS

/etc

0.36

etc

0.21

 combo

0.20

chter

0.18

 combination

0.18

 combos

0.17

etc

0.17

acher

0.15

@hotmail

0.15

/&

0.14

Activations Density 0.123%

terms related to academic or professional roles and practices in various fields

No Comments

No Known Activations