INDEX

Explanations

words related to programming concepts, particularly in Python

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

oux

-0.16

ign

-0.15

adox

-0.14

alted

-0.14

igned

-0.14

rias

-0.14

pill

-0.14

otos

-0.14

commons

-0.14

mouth

-0.13

POSITIVE LOGITS

 hello

0.19

 Hello

0.17

.say

0.16

>Hello

0.16

hello

0.16

Hello

0.16

_HEL

0.16

_hello

0.16

0.15

 Summers

0.15

Activations Density 0.213%

words related to programming concepts, particularly in Python

No Comments

No Known Activations