INDEX

Explanations

elements related to data organization and structure in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ìĸ¸

-0.16

ÏģÎ±ÏĤ

-0.15

ObjectContext

-0.15

 Redistributions

-0.15

Ø±Ø´

-0.14

volution

-0.14

{"

-0.14

ç¦ıåĪ©

-0.14

aps

-0.14

 minor

-0.13

POSITIVE LOGITS

0.29

[:

0.27

(:

0.25

[:

0.25

Symbol

0.19

 except

0.18

 Except

0.18

 Symbol

0.18

Except

0.18

=:

0.17

Activations Density 0.014%

elements related to data organization and structure in code

No Comments

No Known Activations