INDEX

Explanations

phrases related to statistical measurements and projected values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 amounts

-0.19

 numbers

-0.17

 quantities

-0.17

olib

-0.16

PACE

-0.15

numbers

-0.15

 Numbers

-0.15

achu

-0.14

essen

-0.14

iales

-0.14

POSITIVE LOGITS

 total

0.26

 average

0.24

total

0.23

 annual

0.23

 estimated

0.22

average

0.20

 approximate

0.20

annual

0.19

avg

0.19

 maximum

0.19

Activations Density 0.243%

phrases related to statistical measurements and projected values

No Comments

No Known Activations