INDEX

Explanations

topics related to travel accommodations and hotel experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 outings

-0.14

ibrate

-0.14

EdgeInsets

-0.14

aporation

-0.13

 outing

-0.13

outes

-0.13

áº§m

-0.13

 Spor

-0.13

aidu

-0.13

 åĴ

-0.13

POSITIVE LOGITS

 stay

1.04

 staying

1.01

 stays

0.95

 Stay

0.93

 stayed

0.91

stay

0.89

Stay

0.87

 overnight

0.45

 Overnight

0.36

ä½ı

0.35

Activations Density 0.360%

topics related to travel accommodations and hotel experiences

No Comments

No Known Activations