INDEX

Explanations

comments 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

================================================================

-0.21

------------------------------------------------

-0.20

------------------------------------------------------------------------------------------------

-0.20

----------------------------------------------------------------

-0.19

--------------------------------------------------------------------------------

-0.19

////////////////

-0.18

Ø§

-0.17

////////////////////////////////

-0.17

--------------------

-0.17

/////

-0.16

POSITIVE LOGITS

0.23

<![

0.19

 eslint

0.19

TODO

0.18

 ReSharper

0.18

 TODO

0.18

 tslint

0.16

sched

0.15

 Ú©ÙĪÚĨ

0.15

 clang

0.14

Activations Density 0.090%

comments in code

No Comments

No Known Activations