INDEX

Explanations

references to data comparison and manipulation, particularly in programming and writing contexts

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

metis

-0.15

avor

-0.14

ovo

-0.14

upo

-0.14

essel

-0.14

åĿĩ

-0.14

olith

-0.13

ÅĻeb

-0.13

Ban

-0.13

POSITIVE LOGITS

angu

0.18

.helper

0.15

à¹į

0.15

ivy

0.15

 æĹ

0.14

tember

0.14

lington

0.14

à¥Ģà¤µ

0.14

onta

0.14

antics

0.14

Activations Density 0.299%

references to data comparison and manipulation, particularly in programming and writing contexts

No Comments

No Known Activations