INDEX

Explanations

references to "Merlin" or related terms

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

Negative Logits

alar

-0.19

nette

-0.16

-0.15

 Carbon

-0.15

ysis

-0.15

ties

-0.14

eldon

-0.14

sg

-0.14

POSITIVE LOGITS

maid

0.26

maids

0.23

cedes

0.22

seys

0.20

cur

0.20

idian

0.20

oving

0.19

ienda

0.19

dÄ±

0.18

istem

0.18

Activations Density 0.016%

references to "Merlin" or related terms

No Known Activations