INDEX

Explanations

elements related to architecture and historical buildings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

itou

-0.17

cheid

-0.17

nem

-0.14

adas

-0.14

.TryParse

-0.13

\V

-0.13

isseur

-0.13

.addObject

-0.13

Ø¡

-0.13

echa

-0.13

POSITIVE LOGITS

 Kitt

0.16

atic

0.15

ØŃÙĬ

0.15

åº§

0.15

0.14

 Basement

0.14

 Kendrick

0.14

 Zaman

0.14

illiseconds

0.14

Alive

0.14

Activations Density 0.018%

elements related to architecture and historical buildings

No Comments

No Known Activations