INDEX

Explanations

references to various palaces and their significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Nest

-0.15

stick

-0.15

 Freeman

-0.15

-0.14

 ÑģÐºÐ°

-0.14

sb

-0.14

ero

-0.14

("

-0.13

OLF

-0.13

POSITIVE LOGITS

gate

0.16

endir

0.16

oop

0.15

esini

0.15

cone

0.14

ihan

0.14

 TextAlign

0.14

Ú¯Ø±Ø§ÙĨ

0.14

ãĥĩãĤ£

0.14

 luder

0.14

Activations Density 0.011%

references to various palaces and their significance

No Comments

No Known Activations