INDEX

Explanations

mentions of "class" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 McKin

-0.16

usz

-0.16

elson

-0.16

dbl

-0.16

iken

-0.15

to

-0.15

ated

-0.15

/REC

-0.15

ute

-0.14

 Boone

-0.14

POSITIVE LOGITS

ses

0.26

ä¼¼

0.23

ically

0.23

ical

0.23

mates

0.22

ificaÃ§Ã£o

0.21

icism

0.21

 Insecta

0.20

sic

0.20

CastException

0.20

Activations Density 0.026%

mentions of "class" and its variations in different contexts

No Comments

No Known Activations