INDEX

Explanations

details about property features and amenities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

uintptr

-0.15

ores

-0.15

ordum

-0.15

athers

-0.14

á»Ļng

-0.14

adj

-0.14

Baz

-0.14

çµ

-0.14

Ã¼zel

-0.13

okin

-0.13

POSITIVE LOGITS

ignet

0.15

ãĥĶãĥ¼

0.14

ling

0.14

wnd

0.13

udent

0.13

.matcher

0.13

íĤ¹

0.13

 rating

0.13

 ((((

0.13

 Ø±ÙĬ

0.13

Activations Density 0.009%

details about property features and amenities

No Comments

No Known Activations