INDEX

Explanations

phrases and sentences that express criticism or controversy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

gnore

-0.20

 especialmente

-0.19

çī¹åĪ«

-0.18

 surtout

-0.16

 especially

-0.16

pecially

-0.16

 íĬ¹íŀĪ

-0.15

especially

-0.15

 Especially

-0.15

 particularly

-0.15

POSITIVE LOGITS

 sounds

0.36

 Sounds

0.35

Sounds

0.32

sounds

0.30

 sound

0.29

 neat

0.29

 Sound

0.27

 nice

0.26

 sounded

0.26

 cool

0.26

Activations Density 0.293%

phrases and sentences that express criticism or controversy

No Comments

No Known Activations