INDEX

Explanations

mentions of locations and significant 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ø²Ø¯

-0.16

uve

-0.15

éĤ¦

-0.15

apons

-0.15

ulti

-0.15

oldur

-0.15

ultip

-0.14

True

-0.14

ÃŃr

-0.14

 hexadecimal

-0.14

POSITIVE LOGITS

 Florida

0.25

Florida

0.21

 Lauderdale

0.20

iami

0.18

 florida

0.17

orida

0.17

 Keys

0.17

 Saras

0.16

 Tampa

0.16

ï»¿↵↵

0.15

Activations Density 0.464%

mentions of locations and significant geographical identifiers

No Comments

No Known Activations