INDEX

Explanations

geographical names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Essex

-0.18

 Punjab

-0.17

å®ĺ

-0.16

orm

-0.15

 Singh

-0.15

ioni

-0.15

udson

-0.15

_qs

-0.15

ı

-0.14

 Kolkata

-0.14

POSITIVE LOGITS

 Karnataka

0.31

 Seattle

0.31

Seattle

0.28

à²

0.25

 Bangalore

0.25

 Tacoma

0.24

 Minneapolis

0.23

appa

0.23

 à²

0.22

 Spokane

0.22

Activations Density 0.055%

geographical names and locations

No Comments

No Known Activations