INDEX

Explanations

references to customer support interactions and requests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

.scalablytyped

-0.18

nep

-0.14

svp

-0.14

 RSVP

-0.14

imension

-0.13

èĲ½

-0.13

ieux

-0.13

à¸´à¸£

-0.13

ubah

-0.13

TMP

-0.13

POSITIVE LOGITS

 support

0.64

 Support

0.62

support

0.56

Support

0.53

 SUPPORT

0.50

-support

0.50

_support

0.49

.support

0.45

upport

0.43

/support

0.40

Activations Density 0.235%

references to customer support interactions and requests

No Comments

No Known Activations