INDEX

Explanations

technical terms and code-related keywords in programming or software contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

_measurement

-0.16

į

-0.15

ãģ¡

-0.15

assing

-0.14

åĤ

-0.14

yme

-0.14

rape

-0.14

newInstance

-0.14

lyphicon

-0.14

asta

-0.14

POSITIVE LOGITS

 Effect

0.16

ola

0.16

ittle

0.16

essor

0.15

edes

0.15

Effect

0.15

ols

0.15

ullo

0.15

\OptionsResolver

0.14

odd

0.14

Activations Density 0.004%

technical terms and code-related keywords in programming or software contexts

No Comments

No Known Activations