INDEX

Explanations

structural elements and indices 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ugin

-0.20

uh

-0.17

ume

-0.15

cela

-0.15

apol

-0.14

à¸Ĭà¸Ļ

-0.14

 Sorted

-0.14

.userInteractionEnabled

-0.14

assin

-0.13

ÄĽ

-0.13

POSITIVE LOGITS

.BLL

0.15

icz

0.15

onis

0.14

\Id

0.14

åŃ

0.14

.NewLine

0.14

ë³Ħ

0.14

 ********************************************************************************

0.13

_refresh

0.13

ì´Į

0.13

Activations Density 0.204%

structural elements and indices in code

No Comments

No Known Activations