INDEX

Explanations

instances of the word "published" and associated numerical data in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Cave

-0.15

ella

-0.15

omik

-0.15

iegel

-0.15

wine

-0.14

ÑĢÑĥÐ±

-0.14

yle

-0.14

éĩ

-0.14

algo

-0.14

ayne

-0.14

POSITIVE LOGITS

ird

0.15

Voy

0.15

Ð´ÐµÑĢ

0.15

íıĲ

0.15

vez

0.15

ournal

0.15

Ø§ÙĪÙĨØ¯

0.14

 EXEMPLARY

0.14

åĬª

0.14

iid

0.14

Activations Density 0.011%

instances of the word "published" and associated numerical data in various contexts

No Comments

No Known Activations