INDEX

Explanations

references to hotel services and staff interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Backing

-0.16

 backing

-0.15

Ð¾ÑĤÑĥ

-0.15

 ware

-0.15

labs

-0.15

rana

-0.15

andle

-0.14

Ware

-0.14

itou

-0.14

dad

-0.14

POSITIVE LOGITS

 counter

0.48

counter

0.42

 desk

0.40

 Counter

0.39

-counter

0.37

Counter

0.36

 counters

0.34

 reception

0.33

 Desk

0.32

.counter

0.32

Activations Density 0.208%

references to hotel services and staff interactions

No Comments

No Known Activations