INDEX

Explanations

terms related to physical attributes and specifications of products, particularly in the context of vehicles or equipment

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

Negative Logits

ups

-0.16

DD

-0.15

-strong

-0.15

laws

-0.15

 ranks

-0.15

-largest

-0.14

lessness

-0.14

app

-0.14

thing

-0.14

chten

-0.13

POSITIVE LOGITS

 duty

0.20

 haired

0.17

 endian

0.17

 format

0.16

ActionButton

0.15

Īĺ

0.15

ojÃŃ

0.14

ertype

0.14

Porno

0.14

crete

0.14

Activations Density 0.230%

terms related to physical attributes and specifications of products, particularly in the context of vehicles or equipment

No Known Activations