INDEX

Explanations

terms related to perfumes and fragrances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 migliori

-0.15

tega

-0.14

iene

-0.14

 incididunt

-0.14

 Eisen

-0.14

 bona

-0.14

enticator

-0.14

aura

-0.14

IDAD

-0.13

 Ston

-0.13

POSITIVE LOGITS

atos

0.16

ichel

0.15

kop

0.15

æĤł

0.14

zav

0.14

 Dess

0.14

anol

0.14

rire

0.14

0.13

.Unity

0.13

Activations Density 0.012%

terms related to perfumes and fragrances

No Comments

No Known Activations