INDEX

Explanations

elements related to coding options and configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

incare

-0.16

ureka

-0.15

antee

-0.15

_mE

-0.15

:CGRect

-0.15

SocketAddress

-0.15

eman

-0.15

isse

-0.14

pector

-0.14

enstein

-0.14

POSITIVE LOGITS

 corner

0.16

rab

0.15

0.14

 reverse

0.14

 Ð¡Ð¼

0.13

bas

0.13

heimer

0.13

 exit

0.13

 solid

0.13

Activations Density 0.003%

elements related to coding options and configurations

No Comments

No Known Activations