INDEX

Explanations

references to robotics and programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

-resource

-0.15

carbon

-0.15

mon

-0.15

æ¶¨

-0.14

mus

-0.14

 Boss

-0.14

kiem

-0.14

Mus

-0.14

monds

-0.14

Ø¬Ùĩ

-0.14

POSITIVE LOGITS

urtle

0.16

ourke

0.16

adata

0.14

illac

0.14

.connector

0.14

pie

0.14

vag

0.14

enderit

0.14

ÑĥÑĢ

0.14

Pie

0.14

Activations Density 0.180%

references to robotics and programming concepts

No Comments

No Known Activations