INDEX

Explanations

coordinate data relevant to geographic locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

unan

-0.16

.LENGTH

-0.14

acles

-0.14

dsp

-0.13

ocaust

-0.13

å£ģ

-0.13

Domains

-0.13

ypass

-0.13

agate

-0.13

endar

-0.13

POSITIVE LOGITS

lat

0.62

Lat

0.54

 latitude

0.52

lat

0.49

Lat

0.48

 Latitude

0.45

-lat

0.45

latitude

0.42

LAT

0.42

 longitude

0.41

Activations Density 0.108%

coordinate data relevant to geographic locations

No Comments

No Known Activations