INDEX

Explanations

affirmative responses or confirmations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

acie

-0.17

tn

-0.16

tracted

-0.15

ect

-0.15

anca

-0.14

eux

-0.14

.rmi

-0.14

ecture

-0.14

ustry

-0.14

umbo

-0.14

POSITIVE LOGITS

 indeed

0.36

 inde

0.31

enia

0.29

/no

0.29

sir

0.28

 Virginia

0.28

inde

0.26

 sire

0.26

 Indeed

0.26

Indeed

0.25

Activations Density 0.045%

affirmative responses or confirmations

No Comments

No Known Activations