INDEX

Explanations

programming-related terms and data types, particularly boolean values and method signatures

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

-0.17

inery

-0.14

edef

-0.14

ellow

-0.14

serter

-0.14

inx

-0.13

dek

-0.13

ï½¡

-0.13

 dread

-0.13

 facto

-0.13

POSITIVE LOGITS

erokee

0.15

 Olson

0.14

tridge

0.13

 Carlson

0.13

mouseleave

0.13

 âĢĲ

0.13

 Williamson

0.13

_INLINE

0.13

 DISPATCH

0.13

_triggered

0.13

Activations Density 0.013%

programming-related terms and data types, particularly boolean values and method signatures

No Comments

No Known Activations