INDEX

Explanations

phrases related to cost-effectiveness and value in products

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

ael

-0.16

arella

-0.15

NodeType

-0.15

elu

-0.15

Ø¯Ø§ÙĨ

-0.14

Ä±ÅŁÄ±k

-0.14

à¸ģà¸ķ

-0.14

unik

-0.14

 pied

-0.14

.metro

-0.13

POSITIVE LOGITS

ATV

0.27

Pol

0.25

 machines

0.23

AT

0.23

 trail

0.22

 recreational

0.21

AT

0.21

 machine

0.21

(AT

0.21

 side

0.20

Activations Density 0.017%

phrases related to cost-effectiveness and value in products

No Comments

No Known Activations