INDEX

Explanations

references to sponsorship and sponsorship-related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ern

-0.18

ey

-0.15

ten

-0.14

qui

-0.14

enda

-0.14

 Scho

-0.13

erli

-0.13

Ø§ÛĮØ¯

-0.13

eri

-0.13

POSITIVE LOGITS

ships

0.21

apore

0.17

ship

0.16

ë§ģ

0.15

unities

0.15

SHIP

0.15

luet

0.15

INCT

0.15

aleigh

0.15

irts

0.15

Activations Density 0.017%

references to sponsorship and sponsorship-related activities

No Comments

No Known Activations