INDEX

Explanations

expressions of quantity or measurements

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

 same

-0.20

ories

-0.19

orest

-0.16

quel

-0.16

 mesma

-0.16

pieces

-0.15

 invo

-0.15

lew

-0.15

 stesso

-0.15

cot

-0.15

POSITIVE LOGITS

 certain

0.27

iÃ³n

0.24

ione

0.23

idade

0.22

 Certain

0.21

 certo

0.19

 delle

0.19

 degli

0.19

IDADE

0.18

 autre

0.18

Activations Density 0.033%

expressions of quantity or measurements

No Comments

No Known Activations