INDEX

Explanations

expressions related to personal expectations and experiences

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

Not in Any Lists

No Comments

Negative Logits

 minimise

-0.21

 recognise

-0.20

 armour

-0.20

 recognised

-0.20

 rumours

-0.19

 realise

-0.19

 manoe

-0.18

 colourful

-0.18

 specialised

-0.18

POSITIVE LOGITS

pop

0.23

bin

0.23

Pop

0.22

Pop

0.20

 popped

0.20

pop

0.19

 popping

0.19

lia

0.19

 flick

0.19

(pop

0.18

Activations Density 0.501%

expressions related to personal expectations and experiences

No Comments

No Known Activations