INDEX

Explanations

terms related to the process of applying rules or guidelines

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

vern

-0.17

.MaxValue

-0.17

endency

-0.16

ÏĦÎ¿Ïį

-0.15

urus

-0.15

ColumnInfo

-0.15

anke

-0.15

jerne

-0.15

uario

-0.14

ktor

-0.14

POSITIVE LOGITS

 applied

0.28

 apply

0.27

.apply

0.25

 applies

0.25

apply

0.24

 Applied

0.23

 principles

0.22

Applied

0.22

 applying

0.22

 Apply

0.21

Activations Density 0.082%

terms related to the process of applying rules or guidelines

No Comments

No Known Activations