INDEX

Explanations

phrases related to product specifications and features

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anka

-0.16

acs

-0.15

Ð°Ð¶

-0.14

imitÃ©

-0.14

otics

-0.14

sworth

-0.14

éģĵ

-0.13

urg

-0.13

adors

-0.13

 Sach

-0.13

POSITIVE LOGITS

 sold

0.25

 available

0.20

 identical

0.19

 manufactured

0.18

 selling

0.18

selling

0.17

available

0.17

 Sold

0.17

sold

0.17

 Selling

0.17

Activations Density 0.140%

phrases related to product specifications and features

No Comments

No Known Activations