INDEX

Explanations

references to technical expertise and support in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Techniques

-0.20

 technik

-0.20

 Technique

-0.20

otech

-0.19

 Technologies

-0.19

 tecn

-0.19

Tech

-0.18

 teknik

-0.18

 Technology

-0.17

 technology

-0.17

POSITIVE LOGITS

ities

0.38

ity

0.31

ITIES

0.24

.ly

0.21

0.20

/sc

0.19

ITY

0.19

/engine

0.19

ture

0.18

ical

0.18

Activations Density 0.024%

references to technical expertise and support in various contexts

No Comments

No Known Activations