INDEX

Explanations

content related to scheduling and making appointments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ox

-0.18

oxide

-0.16

ubbo

-0.16

 handing

-0.15

 capsules

-0.14

 numberWith

-0.14

asis

-0.14

heim

-0.13

 Lump

-0.13

 Sundays

-0.13

POSITIVE LOGITS

 appointment

0.60

 appointments

0.55

 Appointment

0.53

appointment

0.50

Appointment

0.48

 reservation

0.42

 Reservation

0.40

 booking

0.40

appoint

0.40

 appoint

0.39

Activations Density 0.191%

content related to scheduling and making appointments

No Comments

No Known Activations