INDEX

Explanations

references to names or titles, particularly in entertainment or literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

×¢

-0.16

resh

-0.15

 flatt

-0.14

erez

-0.14

ards

-0.14

aaS

-0.14

ucle

-0.14

oose

-0.14

driver

-0.14

ig

-0.14

POSITIVE LOGITS

ansson

0.18

orough

0.17

venes

0.17

elyn

0.16

ctal

0.16

ernaut

0.16

assic

0.15

endale

0.15

caff

0.15

à¸ªà¸¥

0.15

Activations Density 0.033%

references to names or titles, particularly in entertainment or literature

No Comments

No Known Activations