INDEX

Explanations

phrases related to the action of applying or implementing something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

SnackBar

-0.15

ary

-0.15

ilde

-0.15

ambre

-0.15

meld

-0.14

 IllegalAccessException

-0.14

pill

-0.14

uario

-0.14

urus

-0.14

ColumnInfo

-0.14

POSITIVE LOGITS

 applied

0.25

 apply

0.23

 applies

0.21

 Applied

0.21

apply

0.21

.apply

0.21

 brakes

0.21

Applied

0.21

 Pressure

0.20

 pressure

0.20

Activations Density 0.052%

phrases related to the action of applying or implementing something

No Comments

No Known Activations