INDEX

Explanations

references to geographical locations and their significance

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

á»ĳt

-0.18

Å¼e

-0.15

quine

-0.15

ÑĥÑĪÐºÐ°

-0.14

 unlike

-0.14

itler

-0.14

ddy

-0.14

ako

-0.13

chw

-0.13

 Ending

-0.13

POSITIVE LOGITS

ä¹ĭä¸Ģ

0.30

 EVER

0.25

 ever

0.25

 according

0.23

 vÅ¯bec

0.23

 anywhere

0.22

yet

0.20

 aside

0.20

according

0.19

-ever

0.19

Activations Density 0.195%

references to geographical locations and their significance

No Comments

No Known Activations