INDEX

Explanations

conversational dialogue and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

aroo

-0.15

 MÃ©d

-0.15

egin

-0.15

ynch

-0.15

 DependencyProperty

-0.14

ction

-0.14

chk

-0.14

ToProps

-0.14

ange

-0.14

à¹īà¸²à¸§

-0.14

POSITIVE LOGITS

éĤ£ä¸ª

0.17

kia

0.17

 here

0.17

 ÎµÎºÎµÎ¯

0.17

 orada

0.16

ĻĤ

0.16

erken

0.16

vens

0.16

 THAT

0.16

éĤ£éĩĮ

0.16

Activations Density 0.197%

conversational dialogue and interactions

No Comments

No Known Activations