INDEX

Explanations

references to locations and institutions in Oakland

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Bend

-0.16

 Brew

-0.15

otu

-0.15

.isFile

-0.15

ogs

-0.14

.gb

-0.14

Î±Î½

-0.14

enz

-0.14

à¸Ńà¸ª

-0.14

Î»Î»Î¹

-0.14

POSITIVE LOGITS

 Oakland

0.41

Oak

0.34

 Berkeley

0.30

oak

0.28

Oak

0.25

0.23

Ber

0.22

 Raiders

0.21

ber

0.20

 Berk

0.19

Activations Density 0.055%

references to locations and institutions in Oakland

No Comments

No Known Activations