INDEX

Explanations

addresses and geographical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ubat

-0.20

iez

-0.17

staking

-0.17

rosse

-0.15

din

-0.15

.toJSON

-0.14

StateManager

-0.14

Å¡ov

-0.14

DIC

-0.14

rut

-0.14

POSITIVE LOGITS

GR

0.24

 Grand

0.24

Grand

0.23

GR

0.23

_gr

0.20

 Holland

0.20

 Griff

0.20

èį·

0.19

0.18

-gr

0.18

Activations Density 0.010%

addresses and geographical locations

No Comments

No Known Activations