INDEX

Explanations

enumerations or categorizations in the text

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

iyon

-0.15

linger

-0.14

etc

-0.14

 Canter

-0.14

efa

-0.14

kus

-0.14

UNUSED

-0.14

etc

-0.14

trait

-0.13

	Copyright

-0.13

POSITIVE LOGITS

0.25

:↵

0.23

 depending

0.22

:↵↵

0.21

ãĢĤä¸Ģ

0.19

.First

0.18

depending

0.18

:č↵

0.16

:</

0.16

():

0.16

Activations Density 0.093%

enumerations or categorizations in the text

No Comments

No Known Activations