INDEX

Explanations

references to utilizing skills or resources effectively

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ville

-0.15

 Catch

-0.15

lim

-0.15

 catch

-0.15

adesh

-0.14

 outstanding

-0.13

Catch

-0.13

åĩĮ

-0.13

urons

-0.13

 Bowl

-0.13

POSITIVE LOGITS

use

0.38

use

0.35

-use

0.32

 useful

0.32

 usefulness

0.31

.use

0.30

 Useful

0.30

Use

0.29

Use

0.29

çĶ¨

0.29

Activations Density 0.147%

references to utilizing skills or resources effectively

No Comments

No Known Activations