INDEX

Explanations

terms related to the quantity or amount of something, specifically in a measurable context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.18

Ľ

-0.18

lan

-0.17

rog

-0.17

land

-0.16

like

-0.15

role

-0.15

Î»Î¹

-0.15

rem

-0.15

POSITIVE LOGITS

-volume

0.26

volume

0.22

 volume

0.21

(volume

0.20

.Volume

0.18

.volume

0.18

 Volume

0.18

=length

0.18

capacity

0.17

gii

0.16

Activations Density 0.026%

terms related to the quantity or amount of something, specifically in a measurable context

No Comments

No Known Activations