INDEX

Explanations

quantitative measurements and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ATAB

-0.15

lbs

-0.15

kg

-0.15

apore

-0.14

jin

-0.14

klady

-0.14

aim

-0.14

.apps

-0.13

ales

-0.13

.self

-0.13

POSITIVE LOGITS

AU

0.31

AU

0.27

 light

0.26

 parse

0.24

au

0.23

au

0.23

 Light

0.21

elight

0.21

 LIGHT

0.20

 åħī

0.20

Activations Density 0.017%

quantitative measurements and numerical data

No Comments

No Known Activations