INDEX

Explanations

numerical specifications and measurements of products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

zim

-0.15

ousse

-0.15

Ø¯Ø§Ø¯

-0.15

pym

-0.14

 rims

-0.14

lint

-0.14

awi

-0.13

bruar

-0.13

Äįem

-0.13

.hr

-0.13

POSITIVE LOGITS

 piece

0.30

 Piece

0.28

Piece

0.26

piece

0.25

-piece

0.24

ply

0.21

-layer

0.21

ply

0.21

pc

0.20

_piece

0.20

Activations Density 0.131%

numerical specifications and measurements of products

No Comments

No Known Activations