INDEX

Explanations

references to pricing or cost per unit

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

hoe

-0.16

olini

-0.16

-alist

-0.15

exter

-0.15

NL

-0.15

mmas

-0.15

 Zucker

-0.14

 Styles

-0.14

ppard

-0.14

atches

-0.14

POSITIVE LOGITS

asil

0.16

oft

0.16

0.15

à¥Įà¤°

0.14

missive

0.14

agt

0.14

polator

0.13

 centr

0.13

asString

0.13

age

0.13

Activations Density 0.015%

references to pricing or cost per unit

No Comments

No Known Activations