INDEX

Explanations

references to types of tiles and their applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Crop

-0.16

uckles

-0.15

 Chandler

-0.15

 Cloth

-0.15

rac

-0.15

 cloth

-0.15

á»

-0.14

 fabrics

-0.14

 fabric

-0.14

 Hemp

-0.14

POSITIVE LOGITS

 tiles

0.51

 tile

0.50

 Tile

0.44

 Tiles

0.44

tile

0.42

Tiles

0.40

.tile

0.40

Tile

0.39

tiles

0.39

(tile

0.39

Activations Density 0.036%

references to types of tiles and their applications

No Comments

No Known Activations