INDEX

Explanations

references to the concept of normalcy

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

erior

-0.19

undry

-0.18

ernaut

-0.16

ernet

-0.16

isoft

-0.16

ary

-0.15

eling

-0.15

elic

-0.15

orse

-0.15

lint

-0.15

POSITIVE LOGITS

cy

0.43

ised

0.32

izedName

0.29

mente

0.28

izing

0.27

cies

0.25

isation

0.25

izer

0.25

ise

0.24

ity

0.24

Activations Density 0.022%

references to the concept of normalcy

No Comments

No Known Activations