INDEX

Explanations

references to ships and related maritime terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 shipping

-0.17

_shipping

-0.16

 Shipping

-0.16

qui

-0.16

Ship

-0.16

_ship

-0.16

rias

-0.16

egree

-0.16

 ships

-0.15

éĽ¨

-0.15

POSITIVE LOGITS

yard

0.33

wright

0.30

per

0.30

building

0.29

shape

0.29

yards

0.26

pping

0.25

board

0.23

mates

0.23

pery

0.23

Activations Density 0.014%

references to ships and related maritime terminology

No Comments

No Known Activations