INDEX

Explanations

variations of the word "Max" and related terms indicating maximum values or achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

aug

-0.15

aking

-0.14

uff

-0.14

 sufficient

-0.14

ÅĽli

-0.14

bite

-0.14

brick

-0.14

duct

-0.14

-0.13

oxic

-0.13

POSITIVE LOGITS

imal

0.37

imize

0.34

imo

0.34

IMUM

0.33

Ð¸Ð¼Ð°Ð»ÑĮ

0.33

imizer

0.31

ima

0.30

illary

0.30

ime

0.29

imized

0.28

Activations Density 0.020%

variations of the word "Max" and related terms indicating maximum values or achievements

No Comments

No Known Activations