INDEX

Explanations

details related to comparisons or contrasts in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

assi

-0.19

ãģŁãĤī

-0.17

yonel

-0.16

ijd

-0.15

.toolbox

-0.15

ãĤĤãģĨ

-0.14

iasi

-0.14

 rotterdam

-0.14

antz

-0.14

à¸¢à¸¡

-0.14

POSITIVE LOGITS

 respectively

0.37

 latter

0.36

 respective

0.28

 both

0.27

 each

0.26

 former

0.25

 neither

0.24

each

0.24

both

0.24

Both

0.23

Activations Density 0.339%

details related to comparisons or contrasts in narratives

No Comments

No Known Activations