INDEX

Explanations

references to new beginnings or launches related to products, events, or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ÑģÑİ

-0.16

 ÑĤÐ¾Ð»

-0.14

elt

-0.14

Ð°Ð¹Ð´

-0.14

anky

-0.14

|int

-0.14

iller

-0.14

į¨

-0.14

-era

-0.14

Î¹ÏĥÏĦÎ¿

-0.13

POSITIVE LOGITS

 years

0.37

 last

0.36

 months

0.36

 several

0.32

 weeks

0.32

 recently

0.26

yrs

0.24

last

0.24

years

0.24

 earlier

0.24

Activations Density 0.222%

references to new beginnings or launches related to products, events, or experiences

No Comments

No Known Activations