INDEX

Explanations

the term "urban" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aler

-0.17

erland

-0.16

OME

-0.16

udent

-0.16

aus

-0.15

Ã·

-0.15

ikan

-0.15

oons

-0.14

autop

-0.14

 Blick

-0.14

POSITIVE LOGITS

ization

0.30

ized

0.27

ites

0.25

isation

0.24

/sub

0.23

izing

0.23

ite

0.23

icity

0.22

izations

0.20

ised

0.19

Activations Density 0.011%

the term "urban" in various contexts

No Comments

No Known Activations