INDEX

Explanations

references to educational programs or initiatives

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

esk

-0.23

astle

-0.16

ensi

-0.15

Adj

-0.15

izzo

-0.15

eric

-0.15

autoload

-0.15

 Pont

-0.14

ç©į

-0.14

ìĭ¬

-0.14

POSITIVE LOGITS

 seats

0.30

 admission

0.29

 entrance

0.27

 counselling

0.27

 seat

0.26

 Entrance

0.25

 admissions

0.25

 Admission

0.25

 Seats

0.25

 counseling

0.24

Activations Density 0.011%

references to educational programs or initiatives

No Comments

No Known Activations