INDEX

Explanations

elements and attributes related to programming or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

typeorm

-0.16

ument

-0.15

BuilderInterface

-0.15

atchet

-0.14

 Blasio

-0.14

unal

-0.14

 FStar

-0.14

nock

-0.14

 Bell

-0.14

 WARRANT

-0.14

POSITIVE LOGITS

 Tiles

0.32

tiles

0.30

Tiles

0.30

 tiles

0.29

.tiles

0.27

 Action

0.26

 action

0.26

_tiles

0.25

.action

0.24

.struts

0.24

Activations Density 0.001%

elements and attributes related to programming or markup languages

No Comments

No Known Activations