INDEX

Explanations

type definitions and template programming constructs 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 @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Maz

-0.17

 circumstances

-0.15

.gov

-0.15

 Cout

-0.15

TRANSFER

-0.15

uku

-0.14

erson

-0.14

erty

-0.14

Ð¼Ð°ÑĶ

-0.14

-minded

-0.14

POSITIVE LOGITS

##_

0.21

::~

0.15

dk

0.14

ÏģÏĩ

0.14

 grÃ¡tis

0.14

à¸Ńà¸§

0.14

 Ø§Ø¶

0.13

:::::

0.13

âĻĢ

0.13

_UNDEFINED

0.13

Activations Density 0.009%

type definitions and template programming constructs in code

No Comments

No Known Activations