INDEX

Explanations

references to coding challenges or issues with programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

æĿ¡

-0.17

 Levine

-0.15

pageNumber

-0.15

 deep

-0.14

nodeName

-0.13

akk

-0.13

egas

-0.13

PTR

-0.13

à¤

-0.13

 coal

-0.13

POSITIVE LOGITS

ATAB

0.15

adow

0.15

ÐµÐºÐ°ÑĢ

0.15

iani

0.15

å¨

0.14

 commented

0.14

simp

0.14

Ãªnh

0.14

à¸Ķà¸²

0.14

[code

0.14

Activations Density 0.122%

references to coding challenges or issues with programming

No Comments

No Known Activations