INDEX

Explanations

phrases that describe items or subjects with specific attributes or features, especially those involving coatings or coverings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ignum

-0.16

odore

-0.16

OLUTE

-0.15

Ð»Ð¸Ð²

-0.15

ixel

-0.15

inspace

-0.15

ahat

-0.15

olute

-0.14

glomer

-0.14

IFY

-0.14

POSITIVE LOGITS

 what

0.15

 from

0.15

ro

0.15

 more

0.15

ãĤĬ

0.15

¹Ħ

0.15

ifest

0.14

Activations Density 0.097%

phrases that describe items or subjects with specific attributes or features, especially those involving coatings or coverings

No Comments

No Known Activations