INDEX

Explanations

references to cost and pricing, specifically focusing on expensive and inexpensive items or concepts

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

que

-0.16

eled

-0.15

pic

-0.15

velt

-0.15

icast

-0.15

bom

-0.14

igen

-0.14

tul

-0.14

cki

-0.14

ushima

-0.14

POSITIVE LOGITS

/free

0.27

å¸¯

0.18

liness

0.17

-priced

0.16

isi

0.16

æĺĵ

0.16

($.

0.15

 Jacqu

0.15

 tickets

0.15

erals

0.15

Activations Density 0.045%

references to cost and pricing, specifically focusing on expensive and inexpensive items or concepts

No Comments

No Known Activations