INDEX

Explanations

references to an event or organization name, particularly focusing on a busines or branding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

fÃ¼

-0.19

inia

-0.15

addtogroup

-0.15

ilan

-0.14

mar

-0.14

bell

-0.14

eg

-0.14

ìŀħ

-0.13

POSITIVE LOGITS

ibia

0.22

0.18

ascar

0.18

aste

0.18

adic

0.18

Ø¹ÙĦÙĪÙħ

0.18

coin

0.17

astes

0.16

ÄĽstÃŃ

0.16

ä¿Ĭ

0.16

Activations Density 0.012%

references to an event or organization name, particularly focusing on a busines or branding context

No Comments

No Known Activations