INDEX

Explanations

phrases that discuss conditionality and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ç§ģãģ®

-0.20

mio

-0.15

 benim

-0.15

isman

-0.15

 unser

-0.14

meu

-0.14

"Our

-0.14

“Our

-0.14

æĪĳçļĦ

-0.14

amoto

-0.14

POSITIVE LOGITS

we

0.44

0.42

we

0.33

 Ð¼Ñĭ

0.28

We

0.28

We

0.27

 nÃ³s

0.25

æĪĳä»¬

0.25

 ìļ°ë¦¬ëĬĶ

0.23

 nosotros

0.21

Activations Density 0.460%

phrases that discuss conditionality and relationships

No Comments

No Known Activations