INDEX

Explanations

code related to data manipulation using pandas in Python

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

atte

-0.20

eyse

-0.18

positor

-0.15

DBObject

-0.15

adius

-0.15

ãģªãĤī

-0.14

longleftrightarrow

-0.14

ously

-0.14

ood

-0.14

-bound

-0.14

POSITIVE LOGITS

loc

0.25

.reset

0.24

.drop

0.22

 drop

0.22

loc

0.22

Loc

0.21

reset

0.21

drop

0.20

 drops

0.20

 Drop

0.20

Activations Density 0.008%

code related to data manipulation using pandas in Python

No Comments

No Known Activations