INDEX

Explanations

programming and coding structures, particularly related to network protocols and data handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

afia

-0.15

)((((

-0.14

uzu

-0.14

mites

-0.13

 disgr

-0.13

fone

-0.13

 Ekim

-0.13

antha

-0.13

ÚĨØ§Ø±

-0.13

áº£i

-0.12

POSITIVE LOGITS

ÏĮÎ³

0.17

istrovstvÃŃ

0.15

ÏģÎ¿Ïħ

0.14

ç

0.14

Ĥ¹

0.14

ÂłkW

0.14

ETCH

0.14

herits

0.14

.mj

0.14

merc

0.13

Activations Density 0.087%

programming and coding structures, particularly related to network protocols and data handling

No Comments

No Known Activations