INDEX

Explanations

elements related to education and training programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 organising

-0.26

organisation

-0.25

 organisers

-0.24

 specialised

-0.23

Colour

-0.23

 organised

-0.23

Behaviour

-0.22

 defence

-0.22

 Organisation

-0.22

 coloured

-0.22

POSITIVE LOGITS

 utilizing

0.27

 statewide

0.25

 utilized

0.24

util

0.23

 thru

0.22

 Util

0.21

 utilize

0.21

-util

0.20

 throughout

0.20

 utilization

0.20

Activations Density 1.491%

elements related to education and training programs

No Comments

No Known Activations