INDEX

Explanations

phrases indicating communication and dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ameleon

-0.15

ä¸¤äºº

-0.15

iloc

-0.14

à¸Ĺà¸°

-0.14

ivic

-0.14

ime

-0.14

)__

-0.14

ÃľR

-0.13

iverse

-0.13

POSITIVE LOGITS

0.15

å¸ĥ

0.15

ocker

0.15

oui

0.14

ishi

0.14

thur

0.14

cook

0.14

tee

0.14

 Cook

0.14

Activations Density 0.065%

phrases indicating communication and dialogue

No Comments

No Known Activations