INDEX

Explanations

technical terms and concepts related to data processing and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 your

-0.17

æĤ¨çļĦ

-0.17

your

-0.17

 YOUR

-0.17

ä½łçļĦ

-0.16

 yourself

-0.15

hes

-0.15

 votre

-0.14

ãģ§ãģĹãĤĩãģĨ

-0.14

oney

-0.14

POSITIVE LOGITS

 several

0.17

 roughly

0.16

 some

0.16

XXXX

0.15

Stuff

0.15

 quiero

0.15

 certain

0.15

oeff

0.14

 stuff

0.14

 saya

0.14

Activations Density 0.189%

technical terms and concepts related to data processing and programming

No Comments

No Known Activations