INDEX

Explanations

references to media files and visual content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Sylv

-0.15

lien

-0.14

regs

-0.14

æŁĦ

-0.14

urtles

-0.14

rike

-0.14

 Milky

-0.14

uyá»ħn

-0.14

 independence

-0.13

inerary

-0.13

POSITIVE LOGITS

anos

0.16

ENTE

0.15

ãĥ©ãĥĥãĤ¯

0.15

owell

0.14

ILLA

0.14

ÏģÎ¹Î¿

0.14

urnished

0.14

argout

0.14

anza

0.14

legate

0.14

Activations Density 0.003%

references to media files and visual content

No Comments

No Known Activations