INDEX

Explanations

code-related methods and functions used in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

alon

-0.16

rado

-0.15

olan

-0.15

ampion

-0.14

antha

-0.14

 Bacon

-0.14

eraÃ§Ã£o

-0.14

arro

-0.14

dy

-0.13

tam

-0.13

POSITIVE LOGITS

0.17

Ã¼k

0.14

ÑħÐ¾Ð´Ð¸ÑĤÑĮ

0.14

ously

0.14

:normal

0.14

 drum

0.14

ather

0.13

Activations Density 0.095%

code-related methods and functions used in programming

No Comments

No Known Activations