INDEX

Explanations

specific applications and products designed for particular purposes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ennes

-0.15

uti

-0.14

orial

-0.14

sembling

-0.14

upported

-0.14

controlled

-0.14

á»ĥn

-0.14

represented

-0.14

-controlled

-0.13

Supported

-0.13

POSITIVE LOGITS

 designed

0.62

 intended

0.50

 Designed

0.49

Designed

0.46

 meant

0.44

-designed

0.41

è¨Ńè¨Ī

0.41

 specifically

0.41

 design

0.39

è®¾è®¡

0.37

Activations Density 0.295%

specific applications and products designed for particular purposes

No Comments

No Known Activations