INDEX

Explanations

technical jargon related to programming properties and methods in object-oriented structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

eyin

-0.15

.gb

-0.15

umas

-0.15

 Variety

-0.14

mination

-0.13

hr

-0.13

ricula

-0.13

.qq

-0.13

enes

-0.13

ÛĮØ¯Ùĩ

-0.13

POSITIVE LOGITS

hi

0.16

aland

0.15

ãĥĥãĥĪ

0.15

Hi

0.15

amber

0.14

essaging

0.14

oldemort

0.14

 Latest

0.13

 Sons

0.13

.scalablytyped

0.13

Activations Density 0.140%

technical jargon related to programming properties and methods in object-oriented structures

No Comments

No Known Activations