INDEX

Explanations

patterns in numerical data and statistics related to sports or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 ((__

-0.16

stery

-0.15

raith

-0.15

 incel

-0.15

dera

-0.14

ninger

-0.14

ofday

-0.14

VERTISEMENT

-0.14

itoris

-0.14

ï¿¥

-0.13

POSITIVE LOGITS

but

0.23

 then

0.22

she

0.21

But

0.20

if

0.19

 they

0.19

com

0.18

 They

0.18

0.17

Activations Density 0.909%

patterns in numerical data and statistics related to sports or events

No Comments

No Known Activations