INDEX

Explanations

references to features and limitations of a service or product, particularly in the context of hosting plans

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

æ§

-0.16

isu

-0.16

.hu

-0.15

urre

-0.15

sei

-0.14

 interp

-0.14

inya

-0.14

deo

-0.14

-dismiss

-0.14

POSITIVE LOGITS

itar

0.17

åħįè´¹

0.15

 gratuiti

0.15

 kostenlose

0.14

orate

0.14

 sample

0.14

çĦ¡æĸĻ

0.14

 Cone

0.14

ARGE

0.13

à¸Łà¸£

0.13

Activations Density 0.097%

references to features and limitations of a service or product, particularly in the context of hosting plans

No Comments

No Known Activations