INDEX

Explanations

concepts related to code reuse and efficiency 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 @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

gor

-0.16

fried

-0.15

obi

-0.14

raid

-0.14

nut

-0.14

fly

-0.14

ader

-0.14

ough

-0.14

awi

-0.14

gap

-0.14

POSITIVE LOGITS

 Phelps

0.16

oloj

0.15

ertest

0.15

OOM

0.14

ÄįÃ¡st

0.14

istencia

0.14

arak

0.14

elters

0.14

ustomer

0.14

arsers

0.14

Activations Density 0.007%

concepts related to code reuse and efficiency in programming

No Comments

No Known Activations