INDEX

Explanations

terms related to abstract concepts and structures in programming or object-oriented design

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

stru

-0.15

Ð²Ð¾Ñİ

-0.15

ç©

-0.14

 sensit

-0.14

pend

-0.14

ÑĪÐ¸Ð½

-0.14

opi

-0.14

Ã§ak

-0.14

isin

-0.14

adlo

-0.14

POSITIVE LOGITS

enic

0.16

Yug

0.15

Lol

0.15

 proc

0.15

 Hind

0.15

akh

0.14

ByExample

0.14

enburg

0.14

issan

0.14

heimer

0.14

Activations Density 0.006%

terms related to abstract concepts and structures in programming or object-oriented design

No Comments

No Known Activations