INDEX

Explanations

location addresses and geographical identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

imon

-0.14

 mÃ¼nchen

-0.14

_BIN

-0.14

erus

-0.14

Ã¹ng

-0.14

_REUSE

-0.14

geist

-0.14

èĪ

-0.14

/sql

-0.14

Aub

-0.14

POSITIVE LOGITS

 Duncan

0.25

 Sidney

0.23

 Nano

0.23

Nan

0.22

 Juan

0.21

 Victoria

0.21

 Chem

0.21

Cow

0.21

Nano

0.21

Sa

0.20

Activations Density 0.013%

location addresses and geographical identifiers

No Comments

No Known Activations