INDEX

Explanations

specific geographical locations and associated addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

enna

-0.15

Kit

-0.15

å¾ģ

-0.14

eva

-0.14

ÙİØ¯

-0.14

oyer

-0.14

ÑĥÑĤÐ¸

-0.14

fen

-0.14

poons

-0.14

POSITIVE LOGITS

zip

0.25

Zip

0.23

Zip

0.23

_zip

0.21

ZIP

0.21

zip

0.21

(zip

0.20

 zipcode

0.20

.Zip

0.19

ZIP

0.18

Activations Density 0.067%

specific geographical locations and associated addresses

No Comments

No Known Activations