INDEX

Explanations

geographical features and boundaries

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

 GÃ¼ven

-0.15

midd

-0.15

taÅŁ

-0.15

 fitte

-0.15

 Gratuit

-0.15

 plat

-0.15

Ð¾ÑĤÐ¾Ð²

-0.15

ires

-0.15

 Berger

-0.14

.central

-0.14

POSITIVE LOGITS

 border

0.25

 borders

0.23

 shared

0.21

 shares

0.20

 Border

0.20

 bordered

0.19

 touches

0.18

 touch

0.18

 touching

0.18

border

0.18

Activations Density 0.020%

geographical features and boundaries

No Comments

No Known Activations