INDEX

Explanations

references to significant works of art and their historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

arcy

-0.16

outil

-0.14

.Dependency

-0.14

 Authors

-0.14

argon

-0.14

vailability

-0.14

Interstitial

-0.13

 facility

-0.13

-CN

-0.13

zdy

-0.13

POSITIVE LOGITS

á»ĭ

0.16

insk

0.15

ycle

0.15

 executed

0.14

 Studies

0.14

 sights

0.14

 Oaks

0.14

lesen

0.14

 Exec

0.14

 oils

0.14

Activations Density 0.065%

references to significant works of art and their historical context

No Comments

No Known Activations