INDEX

Explanations

phrases related to recognition and acknowledgment in various contexts

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

.Expressions

-0.15

thood

-0.15

ÑĤÑĢÐ¾Ð½

-0.14

aterno

-0.14

_codec

-0.14

ahat

-0.14

Ø§ÙĪØª

-0.14

cab

-0.14

codec

-0.14

Ä¾

-0.13

POSITIVE LOGITS

 credit

1.46

 Credit

1.27

credit

1.21

 credits

1.20

Credit

1.14

 Credits

1.05

_credit

1.00

 crÃ©d

0.99

.credit

0.96

credits

0.96

Activations Density 0.184%

phrases related to recognition and acknowledgment in various contexts

No Comments

No Known Activations