INDEX

Explanations

mentions of New Zealand and its related abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

oret

-0.15

uiten

-0.15

ritz

-0.15

rente

-0.14

OrElse

-0.14

antee

-0.14

agher

-0.14

TEGR

-0.14

stell

-0.14

 dÃŃ

-0.13

POSITIVE LOGITS

ers

0.36

 Herald

0.23

 dollar

0.18

-wide

0.18

oids

0.18

ERS

0.18

-born

0.17

/New

0.17

ÐµÑĢÑĪ

0.16

 wide

0.16

Activations Density 0.009%

mentions of New Zealand and its related abbreviations

No Comments

No Known Activations