INDEX

Explanations

references to hospitality and hotel accommodations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

acha

-0.16

itted

-0.15

ì²Ļ

-0.15

Ð¿Ð°

-0.15

alat

-0.15

Ð°Ð²Ð¸

-0.14

preci

-0.14

assi

-0.14

lom

-0.14

orean

-0.14

POSITIVE LOGITS

 swimming

0.16

alth

0.16

iffe

0.15

alt

0.15

uez

0.15

anh

0.15

 Priv

0.14

 Forbes

0.14

ALT

0.14

setLabel

0.14

Activations Density 0.073%

references to hospitality and hotel accommodations

No Comments

No Known Activations