INDEX

Explanations

section headings or labels in the document

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

idy

-0.15

iring

-0.14

iego

-0.14

ired

-0.14

iasi

-0.14

 fits

-0.14

ãĥ³ãĤ¯

-0.14

.metro

-0.13

terms

-0.13

 Ange

-0.13

POSITIVE LOGITS

YL

0.15

NC

0.14

kop

0.14

embourg

0.14

à¹īà¸²à¸ŀ

0.14

/Dk

0.14

bery

0.13

 shortly

0.13

Activations Density 0.004%

section headings or labels in the document

No Comments

No Known Activations